initial commit

2025-06-14 21:18:24 +08:00
commit b03507ab4e
35 changed files with 2349 additions and 0 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -0,0 +1,25 @@
+# ignore .git related folders
+.git/
+.github/
+.gitignore
+# ignore docs
+docs/
+# copy in licenses folder to the container
+!docs/licenses/
+# ignore logs
+**/logs/
+**/runs/
+**/output/*
+**/outputs/*
+**/videos/*
+*.tmp
+# ignore docker
+docker/cluster/exports/
+docker/.container.cfg
+# ignore recordings
+recordings/
+# ignore __pycache__
+**/__pycache__/
+**/*.egg-info/
+# ignore isaac sim symlink
+_isaac_sim?
--- a/.flake8
+++ b/.flake8
@@ -0,0 +1,23 @@
+[flake8]
+show-source=True
+statistics=True
+per-file-ignores=*/__init__.py:F401
+# E402: Module level import not at top of file
+# E501: Line too long
+# W503: Line break before binary operator
+# E203: Whitespace before ':' -> conflicts with black
+# D401: First line should be in imperative mood
+# R504: Unnecessary variable assignment before return statement.
+# R505: Unnecessary elif after return statement
+# SIM102: Use a single if-statement instead of nested if-statements
+# SIM117: Merge with statements for context managers that have same scope.
+# SIM118: Checks for key-existence checks against dict.keys() calls.
+ignore=E402,E501,W503,E203,D401,R504,R505,SIM102,SIM117,SIM118
+max-line-length = 120
+max-complexity = 30
+exclude=_*,.vscode,.git,docs/**
+# docstrings
+docstring-convention=google
+# annotations
+suppress-none-returning=True
+allow-star-arg-any=True
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,12 @@
+*.usd filter=lfs diff=lfs merge=lfs -text
+*.usda filter=lfs diff=lfs merge=lfs -text
+*.psd filter=lfs diff=lfs merge=lfs -text
+*.hdr filter=lfs diff=lfs merge=lfs -text
+*.dae filter=lfs diff=lfs merge=lfs -text
+*.mtl filter=lfs diff=lfs merge=lfs -text
+*.obj filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.jit filter=lfs diff=lfs merge=lfs -text
+*.hdf5 filter=lfs diff=lfs merge=lfs -text
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,68 @@
+# C++
+**/cmake-build*/
+**/build*/
+**/*.so
+**/*.log*
+
+# Omniverse
+**/*.dmp
+**/.thumbs
+
+# No USD files allowed in the repo
+**/*.usd
+**/*.usda
+**/*.usdc
+**/*.usdz
+
+# Python
+.DS_Store
+**/*.egg-info/
+**/__pycache__/
+**/.pytest_cache/
+**/*.pyc
+**/*.pb
+
+# Docker/Singularity
+**/*.sif
+docker/cluster/exports/
+docker/.container.cfg
+
+# IDE
+**/.idea/
+**/.vscode/
+# Don't ignore the top-level .vscode directory as it is
+# used to configure VS Code settings
+!.vscode
+
+# Outputs
+**/output/*
+**/outputs/*
+**/videos/*
+**/wandb/*
+**/.neptune/*
+docker/artifacts/
+*.tmp
+
+# Doc Outputs
+**/docs/_build/*
+**/generated/*
+
+# Isaac-Sim packman
+_isaac_sim*
+_repo
+_build
+.lastformat
+
+# RL-Games
+**/runs/*
+**/logs/*
+**/recordings/*
+
+# Pre-Trained Checkpoints
+/.pretrained_checkpoints/
+
+# Teleop Recorded Dataset
+datasets
+
+# Tests
+tests/
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,81 @@
+repos:
+  - repo: https://github.com/python/black
+    rev: 24.3.0
+    hooks:
+      - id: black
+        args: ["--line-length", "120", "--unstable"]
+  - repo: https://github.com/pycqa/flake8
+    rev: 7.0.0
+    hooks:
+      - id: flake8
+        additional_dependencies: [flake8-simplify, flake8-return]
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-symlinks
+      - id: destroyed-symlinks
+      - id: check-added-large-files
+        args: ["--maxkb=2000"]  # restrict files more than 2 MB. Should use git-lfs instead.
+      - id: check-yaml
+      - id: check-merge-conflict
+      - id: check-case-conflict
+      - id: check-executables-have-shebangs
+      - id: check-toml
+      - id: end-of-file-fixer
+      - id: check-shebang-scripts-are-executable
+      - id: detect-private-key
+      - id: debug-statements
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        name: isort (python)
+        args: ["--profile", "black", "--filter-files"]
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.15.1
+    hooks:
+      - id: pyupgrade
+        args: ["--py310-plus"]
+        # FIXME: This is a hack because Pytorch does not like: torch.Tensor | dict aliasing
+        exclude: "source/isaaclab/isaaclab/envs/common.py|source/isaaclab/isaaclab/ui/widgets/image_plot.py|source/isaaclab_tasks/isaaclab_tasks/direct/humanoid_amp/motions/motion_loader.py"
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.6
+    hooks:
+      - id: codespell
+        additional_dependencies:
+        - tomli
+        exclude: "CONTRIBUTORS.md"
+  # FIXME: Figure out why this is getting stuck under VPN.
+  # - repo: https://github.com/RobertCraigie/pyright-python
+  #   rev: v1.1.315
+  #   hooks:
+  #   - id: pyright
+  - repo: https://github.com/Lucas-C/pre-commit-hooks
+    rev: v1.5.1
+    hooks:
+      - id: insert-license
+        files: \.py$
+        args:
+          # - --remove-header    # Remove existing license headers. Useful when updating license.
+          - --license-filepath
+          - .github/LICENSE_HEADER.txt
+          - --use-current-year
+        exclude: "source/isaaclab_mimic/|scripts/imitation_learning/isaaclab_mimic/"
+  # Apache 2.0 license for mimic files
+  - repo: https://github.com/Lucas-C/pre-commit-hooks
+    rev: v1.5.1
+    hooks:
+      - id: insert-license
+        files: ^(source/isaaclab_mimic|scripts/imitation_learning/isaaclab_mimic)/.*\.py$
+        args:
+          # - --remove-header    # Remove existing license headers. Useful when updating license.
+          - --license-filepath
+          - .github/LICENSE_HEADER_MIMIC.txt
+          - --use-current-year
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.10.0
+    hooks:
+      - id: rst-backticks
+      - id: rst-directive-colons
+      - id: rst-inline-touching-normal
--- a/.vscode/.gitignore
+++ b/.vscode/.gitignore
@@ -0,0 +1,10 @@
+# Note: These files are kept for development purposes only.
+!tools/launch.template.json
+!tools/settings.template.json
+!tools/setup_vscode.py
+!extensions.json
+!tasks.json
+
+# Ignore all other files
+.python.env
+*.json
--- a/.vscode/extensions.json
+++ b/.vscode/extensions.json
@@ -0,0 +1,12 @@
+{
+	// See http://go.microsoft.com/fwlink/?LinkId=827846
+	// for the documentation about the extensions.json format
+	"recommendations": [
+		"ms-python.python",
+		"ms-python.vscode-pylance",
+		"ban.spellright",
+		"ms-iot.vscode-ros",
+		"ms-python.black-formatter",
+		"ms-python.flake8",
+	]
+}
--- a/.vscode/tasks.json
+++ b/.vscode/tasks.json
@@ -0,0 +1,23 @@
+{
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "setup_python_env",
+            "type": "shell",
+            "linux": {
+                "command": "${input:isaac_path}/python.sh ${workspaceFolder}/.vscode/tools/setup_vscode.py --isaac_path ${input:isaac_path}"
+            },
+            "windows": {
+                "command": "${input:isaac_path}/python.bat ${workspaceFolder}/.vscode/tools/setup_vscode.py --isaac_path ${input:isaac_path}"
+            }
+        }
+    ],
+    "inputs": [
+        {
+            "id": "isaac_path",
+            "description": "Absolute path to the current Isaac Sim installation. Can be skipped if Isaac Sim installed from pip.",
+            "default": "${HOME}/isaacsim",
+            "type": "promptString"
+        },
+    ]
+}
--- a/.vscode/tools/launch.template.json
+++ b/.vscode/tools/launch.template.json
@@ -0,0 +1,103 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        // For standalone script execution
+        {
+            "name": "Python: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+        },
+        {
+            "name": "Python: Train Template-Flexr-V0-Direct-v0 with rl_games (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "4096", "--headless"],
+            "program": "${workspaceFolder}/scripts/rl_games/train.py",
+            "console": "integratedTerminal",
+        },
+        {
+            "name": "Python: Play Template-Flexr-V0-Direct-v0 with rl_games (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "32"],
+            "program": "${workspaceFolder}/scripts/rl_games/play.py",
+            "console": "integratedTerminal",
+        },
+        {
+            "name": "Python: Train Template-Flexr-V0-Direct-v0 with rsl_rl (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "4096", "--headless"],
+            "program": "${workspaceFolder}/scripts/rsl_rl/train.py",
+            "console": "integratedTerminal",
+        },
+        {
+            "name": "Python: Play Template-Flexr-V0-Direct-v0 with rsl_rl (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "32"],
+            "program": "${workspaceFolder}/scripts/rsl_rl/play.py",
+            "console": "integratedTerminal",
+        },
+        // For script execution inside a Docker
+        {
+            "name": "Docker: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${env:PYTHONPATH}:${workspaceFolder}"
+            }
+        },
+        {
+            "name": "Docker: Train Template-Flexr-V0-Direct-v0 with rl_games (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "4096", "--headless"],
+            "program": "${workspaceFolder}/scripts/rl_games/train.py",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${env:PYTHONPATH}:${workspaceFolder}"
+            },
+        },
+        {
+            "name": "Docker: Play Template-Flexr-V0-Direct-v0 with rl_games (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "32"],
+            "program": "${workspaceFolder}/scripts/rl_games/play.py",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${env:PYTHONPATH}:${workspaceFolder}"
+            },
+        },
+        {
+            "name": "Docker: Train Template-Flexr-V0-Direct-v0 with rsl_rl (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "4096", "--headless"],
+            "program": "${workspaceFolder}/scripts/rsl_rl/train.py",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${env:PYTHONPATH}:${workspaceFolder}"
+            },
+        },
+        {
+            "name": "Docker: Play Template-Flexr-V0-Direct-v0 with rsl_rl (PPO)",
+            "type": "debugpy",
+            "request": "launch",
+            "args" : ["--task", "Template-Flexr-V0-Direct-v0", "--num_envs", "32"],
+            "program": "${workspaceFolder}/scripts/rsl_rl/play.py",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${env:PYTHONPATH}:${workspaceFolder}"
+            },
+        },
+    ]
+}
--- a/.vscode/tools/settings.template.json
+++ b/.vscode/tools/settings.template.json
@@ -0,0 +1,86 @@
+{
+    "files.associations": {
+        "*.tpp": "cpp",
+        "*.kit": "toml",
+        "*.rst": "restructuredtext"
+    },
+    "editor.rulers": [120],
+
+    // files to be ignored by the linter
+    "files.watcherExclude": {
+        "**/.git/objects/**": true,
+        "**/.git/subtree-cache/**": true,
+        "**/node_modules/**": true,
+        "**/_isaac_sim/**": true,
+        "**/_compiler/**": true
+    },
+    // Configuration for spelling checker
+    "spellright.language": [
+        "en-US-10-1."
+    ],
+    "spellright.documentTypes": [
+        "markdown",
+        "latex",
+        "plaintext",
+        "cpp",
+        "asciidoc",
+        "python",
+        "restructuredtext"
+    ],
+    "cSpell.words": [
+        "literalinclude",
+        "linenos",
+        "instanceable",
+        "isaacSim",
+        "jacobians",
+        "pointcloud",
+        "ridgeback",
+        "rllib",
+        "robomimic",
+        "teleoperation",
+        "xform",
+        "numpy",
+        "tensordict",
+        "flatcache",
+        "physx",
+        "dpad",
+        "gamepad",
+        "linspace",
+        "upsampled",
+        "downsampled",
+        "arange",
+        "discretization",
+        "trimesh",
+        "uninstanceable"
+    ],
+    // This enables python language server. Seems to work slightly better than jedi:
+    "python.languageServer": "Pylance",
+    // We use "black" as a formatter:
+    "python.formatting.provider": "black",
+    "python.formatting.blackArgs": ["--line-length", "120"],
+    // Use flake8 for linting
+    "python.linting.pylintEnabled": false,
+    "python.linting.flake8Enabled": true,
+    "python.linting.flake8Args": [
+        "--max-line-length=120"
+    ],
+    // Use docstring generator
+    "autoDocstring.docstringFormat": "google",
+    "autoDocstring.guessTypes": true,
+    // Python environment path
+    // note: the default interpreter is overridden when user selects a workspace interpreter
+    //     in the status bar. For example, the virtual environment python interpreter
+    "python.defaultInterpreterPath": "",
+    // ROS distribution
+    "ros.distro": "noetic",
+    // Language specific settings
+    "[python]": {
+        "editor.tabSize": 4
+    },
+    "[restructuredtext]": {
+        "editor.tabSize": 2
+    },
+    // Python extra paths
+    // Note: this is filled up when vscode is set up for the first time
+    "python.analysis.extraPaths": []
+}
--- a/.vscode/tools/setup_vscode.py
+++ b/.vscode/tools/setup_vscode.py
@@ -0,0 +1,220 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""This script sets up the vs-code settings for the Isaac Lab project.
+
+This script merges the python.analysis.extraPaths from the "{ISAACSIM_DIR}/.vscode/settings.json" file into
+the ".vscode/settings.json" file.
+
+This is necessary because Isaac Sim 2022.2.1 onwards does not add the necessary python packages to the python path
+when the "setup_python_env.sh" is run as part of the vs-code launch configuration.
+"""
+
+import argparse
+import os
+import pathlib
+import platform
+import re
+import sys
+
+PROJECT_DIR = pathlib.Path(__file__).parents[2]
+"""Path to the the project directory."""
+
+try:
+    import isaacsim  # noqa: F401
+
+    isaacsim_dir = os.environ.get("ISAAC_PATH", "")
+except ModuleNotFoundError or ImportError:
+    # Create a parser to get the isaac-sim path
+    parser = argparse.ArgumentParser(description="Setup the VSCode settings for the project.")
+    parser.add_argument("--isaac_path", type=str, help="The absolute path to the Isaac Sim installation.")
+    args = parser.parse_args()
+
+    # parse the isaac-sim directory
+    isaacsim_dir = args.isaac_path
+    # check if the isaac-sim directory is provided
+    if not os.path.exists(isaacsim_dir):
+        raise FileNotFoundError(
+            f"Could not find the isaac-sim directory: {isaacsim_dir}. Please provide the correct path to the Isaac Sim"
+            " installation."
+        )
+except EOFError:
+    print("Unable to trigger EULA acceptance. This is likely due to the script being run in a non-interactive shell.")
+    print("Please run the script in an interactive shell to accept the EULA.")
+    print("Skipping the setup of the VSCode settings...")
+    sys.exit(0)
+
+# check if the isaac-sim directory exists
+if not os.path.exists(isaacsim_dir):
+    raise FileNotFoundError(
+        f"Could not find the isaac-sim directory: {isaacsim_dir}. There are two possible reasons for this:"
+        "\n\t1. The Isaac Sim directory does not exist as provided CLI path."
+        "\n\t2. The script could import the 'isaacsim' package. This could be due to the 'isaacsim' package not being "
+        "installed in the Python environment.\n"
+        "\nPlease make sure that the Isaac Sim directory exists or that the 'isaacsim' package is installed."
+    )
+
+ISAACSIM_DIR = isaacsim_dir
+"""Path to the isaac-sim directory."""
+
+
+def overwrite_python_analysis_extra_paths(isaaclab_settings: str) -> str:
+    """Overwrite the python.analysis.extraPaths in the Isaac Lab settings file.
+
+    The extraPaths are replaced with the path names from the isaac-sim settings file that exists in the
+    "{ISAACSIM_DIR}/.vscode/settings.json" file.
+
+    If the isaac-sim settings file does not exist, the extraPaths are not overwritten.
+
+    Args:
+        isaaclab_settings: The settings string to use as template.
+
+    Returns:
+        The settings string with overwritten python analysis extra paths.
+    """
+    # isaac-sim settings
+    isaacsim_vscode_filename = os.path.join(ISAACSIM_DIR, ".vscode", "settings.json")
+
+    # we use the isaac-sim settings file to get the python.analysis.extraPaths for kit extensions
+    # if this file does not exist, we will not add any extra paths
+    if os.path.exists(isaacsim_vscode_filename):
+        # read the path names from the isaac-sim settings file
+        with open(isaacsim_vscode_filename) as f:
+            vscode_settings = f.read()
+        # extract the path names
+        # search for the python.analysis.extraPaths section and extract the contents
+        settings = re.search(
+            r"\"python.analysis.extraPaths\": \[.*?\]", vscode_settings, flags=re.MULTILINE | re.DOTALL
+        )
+        settings = settings.group(0)
+        settings = settings.split('"python.analysis.extraPaths": [')[-1]
+        settings = settings.split("]")[0]
+
+        # read the path names from the isaac-sim settings file
+        path_names = settings.split(",")
+        path_names = [path_name.strip().strip('"') for path_name in path_names]
+        path_names = [path_name for path_name in path_names if len(path_name) > 0]
+
+        # change the path names to be relative to the Isaac Lab directory
+        rel_path = os.path.relpath(ISAACSIM_DIR, PROJECT_DIR)
+        path_names = ['"${workspaceFolder}/' + rel_path + "/" + path_name + '"' for path_name in path_names]
+    else:
+        path_names = []
+        print(
+            f"[WARN] Could not find Isaac Sim VSCode settings: {isaacsim_vscode_filename}."
+            "\n\tThis will result in missing 'python.analysis.extraPaths' in the VSCode"
+            "\n\tsettings, which limits the functionality of the Python language server."
+            "\n\tHowever, it does not affect the functionality of the Isaac Lab project."
+            "\n\tWe are working on a fix for this issue with the Isaac Sim team."
+        )
+
+    # add the path names that are in the Isaac Lab extensions directory
+    isaaclab_extensions = os.listdir(os.path.join(PROJECT_DIR, "source"))
+    path_names.extend(['"${workspaceFolder}/source/' + ext + '"' for ext in isaaclab_extensions])
+
+    # combine them into a single string
+    path_names = ",\n\t\t".expandtabs(4).join(path_names)
+    # deal with the path separator being different on Windows and Unix
+    path_names = path_names.replace("\\", "/")
+
+    # replace the path names in the Isaac Lab settings file with the path names parsed
+    isaaclab_settings = re.sub(
+        r"\"python.analysis.extraPaths\": \[.*?\]",
+        '"python.analysis.extraPaths": [\n\t\t'.expandtabs(4) + path_names + "\n\t]".expandtabs(4),
+        isaaclab_settings,
+        flags=re.DOTALL,
+    )
+    # return the Isaac Lab settings string
+    return isaaclab_settings
+
+
+def overwrite_default_python_interpreter(isaaclab_settings: str) -> str:
+    """Overwrite the default python interpreter in the Isaac Lab settings file.
+
+    The default python interpreter is replaced with the path to the python interpreter used by the
+    isaac-sim project. This is necessary because the default python interpreter is the one shipped with
+    isaac-sim.
+
+    Args:
+        isaaclab_settings: The settings string to use as template.
+
+    Returns:
+        The settings string with overwritten default python interpreter.
+    """
+    # read executable name
+    python_exe = os.path.normpath(sys.executable)
+
+    # replace with Isaac Sim's python.sh or python.bat scripts to make sure python with correct
+    # source paths is set as default
+    if f"kit{os.sep}python{os.sep}bin{os.sep}python" in python_exe:
+        # Check if the OS is Windows or Linux to use appropriate shell file
+        if platform.system() == "Windows":
+            python_exe = python_exe.replace(f"kit{os.sep}python{os.sep}bin{os.sep}python3", "python.bat")
+        else:
+            python_exe = python_exe.replace(f"kit{os.sep}python{os.sep}bin{os.sep}python3", "python.sh")
+
+    # replace the default python interpreter in the Isaac Lab settings file with the path to the
+    # python interpreter in the Isaac Lab directory
+    isaaclab_settings = re.sub(
+        r"\"python.defaultInterpreterPath\": \".*?\"",
+        f'"python.defaultInterpreterPath": "{python_exe}"',
+        isaaclab_settings,
+        flags=re.DOTALL,
+    )
+    # return the Isaac Lab settings file
+    return isaaclab_settings
+
+
+def main():
+    # Isaac Lab template settings
+    isaaclab_vscode_template_filename = os.path.join(PROJECT_DIR, ".vscode", "tools", "settings.template.json")
+    # make sure the Isaac Lab template settings file exists
+    if not os.path.exists(isaaclab_vscode_template_filename):
+        raise FileNotFoundError(
+            f"Could not find the Isaac Lab template settings file: {isaaclab_vscode_template_filename}"
+        )
+    # read the Isaac Lab template settings file
+    with open(isaaclab_vscode_template_filename) as f:
+        isaaclab_template_settings = f.read()
+
+    # overwrite the python.analysis.extraPaths in the Isaac Lab settings file with the path names
+    isaaclab_settings = overwrite_python_analysis_extra_paths(isaaclab_template_settings)
+    # overwrite the default python interpreter in the Isaac Lab settings file with the path to the
+    # python interpreter used to call this script
+    isaaclab_settings = overwrite_default_python_interpreter(isaaclab_settings)
+
+    # add template notice to the top of the file
+    header_message = (
+        "// This file is a template and is automatically generated by the setup_vscode.py script.\n"
+        "// Do not edit this file directly.\n"
+        "// \n"
+        f"// Generated from: {isaaclab_vscode_template_filename}\n"
+    )
+    isaaclab_settings = header_message + isaaclab_settings
+
+    # write the Isaac Lab settings file
+    isaaclab_vscode_filename = os.path.join(PROJECT_DIR, ".vscode", "settings.json")
+    with open(isaaclab_vscode_filename, "w") as f:
+        f.write(isaaclab_settings)
+
+    # copy the launch.json file if it doesn't exist
+    isaaclab_vscode_launch_filename = os.path.join(PROJECT_DIR, ".vscode", "launch.json")
+    isaaclab_vscode_template_launch_filename = os.path.join(PROJECT_DIR, ".vscode", "tools", "launch.template.json")
+    if not os.path.exists(isaaclab_vscode_launch_filename):
+        # read template launch settings
+        with open(isaaclab_vscode_template_launch_filename) as f:
+            isaaclab_template_launch_settings = f.read()
+        # add header
+        header_message = header_message.replace(
+            isaaclab_vscode_template_filename, isaaclab_vscode_template_launch_filename
+        )
+        isaaclab_launch_settings = header_message + isaaclab_template_launch_settings
+        # write the Isaac Lab launch settings file
+        with open(isaaclab_vscode_launch_filename, "w") as f:
+            f.write(isaaclab_launch_settings)
+
+
+if __name__ == "__main__":
+    main()
--- a/README.md
+++ b/README.md
@@ -0,0 +1,135 @@
+# Template for Isaac Lab Projects
+
+## Overview
+
+This project/repository serves as a template for building projects or extensions based on Isaac Lab.
+It allows you to develop in an isolated environment, outside of the core Isaac Lab repository.
+
+**Key Features:**
+
+- `Isolation` Work outside the core Isaac Lab repository, ensuring that your development efforts remain self-contained.
+- `Flexibility` This template is set up to allow your code to be run as an extension in Omniverse.
+
+**Keywords:** extension, template, isaaclab
+
+## Installation
+
+- Install Isaac Lab by following the [installation guide](https://isaac-sim.github.io/IsaacLab/main/source/setup/installation/index.html).
+  We recommend using the conda installation as it simplifies calling Python scripts from the terminal.
+
+- Clone or copy this project/repository separately from the Isaac Lab installation (i.e. outside the `IsaacLab` directory):
+
+- Using a python interpreter that has Isaac Lab installed, install the library in editable mode using:
+
+    ```bash
+    # use 'PATH_TO_isaaclab.sh|bat -p' instead of 'python' if Isaac Lab is not installed in Python venv or conda
+    python -m pip install -e source/FLEXR_v0
+
+- Verify that the extension is correctly installed by:
+
+    - Listing the available tasks:
+
+        Note: It the task name changes, it may be necessary to update the search pattern `"Template-"`
+        (in the `scripts/list_envs.py` file) so that it can be listed.
+
+        ```bash
+        # use 'FULL_PATH_TO_isaaclab.sh|bat -p' instead of 'python' if Isaac Lab is not installed in Python venv or conda
+        python scripts/list_envs.py
+        ```
+
+    - Running a task:
+
+        ```bash
+        # use 'FULL_PATH_TO_isaaclab.sh|bat -p' instead of 'python' if Isaac Lab is not installed in Python venv or conda
+        python scripts/<RL_LIBRARY>/train.py --task=<TASK_NAME>
+        ```
+
+    - Running a task with dummy agents:
+
+        These include dummy agents that output zero or random agents. They are useful to ensure that the environments are configured correctly.
+
+        - Zero-action agent
+
+            ```bash
+            # use 'FULL_PATH_TO_isaaclab.sh|bat -p' instead of 'python' if Isaac Lab is not installed in Python venv or conda
+            python scripts/zero_agent.py --task=<TASK_NAME>
+            ```
+        - Random-action agent
+
+            ```bash
+            # use 'FULL_PATH_TO_isaaclab.sh|bat -p' instead of 'python' if Isaac Lab is not installed in Python venv or conda
+            python scripts/random_agent.py --task=<TASK_NAME>
+            ```
+
+### Set up IDE (Optional)
+
+To setup the IDE, please follow these instructions:
+
+- Run VSCode Tasks, by pressing `Ctrl+Shift+P`, selecting `Tasks: Run Task` and running the `setup_python_env` in the drop down menu.
+  When running this task, you will be prompted to add the absolute path to your Isaac Sim installation.
+
+If everything executes correctly, it should create a file .python.env in the `.vscode` directory.
+The file contains the python paths to all the extensions provided by Isaac Sim and Omniverse.
+This helps in indexing all the python modules for intelligent suggestions while writing code.
+
+### Setup as Omniverse Extension (Optional)
+
+We provide an example UI extension that will load upon enabling your extension defined in `source/FLEXR_v0/FLEXR_v0/ui_extension_example.py`.
+
+To enable your extension, follow these steps:
+
+1. **Add the search path of this project/repository** to the extension manager:
+    - Navigate to the extension manager using `Window` -> `Extensions`.
+    - Click on the **Hamburger Icon**, then go to `Settings`.
+    - In the `Extension Search Paths`, enter the absolute path to the `source` directory of this project/repository.
+    - If not already present, in the `Extension Search Paths`, enter the path that leads to Isaac Lab's extension directory directory (`IsaacLab/source`)
+    - Click on the **Hamburger Icon**, then click `Refresh`.
+
+2. **Search and enable your extension**:
+    - Find your extension under the `Third Party` category.
+    - Toggle it to enable your extension.
+
+## Code formatting
+
+We have a pre-commit template to automatically format your code.
+To install pre-commit:
+
+```bash
+pip install pre-commit
+```
+
+Then you can run pre-commit with:
+
+```bash
+pre-commit run --all-files
+```
+
+## Troubleshooting
+
+### Pylance Missing Indexing of Extensions
+
+In some VsCode versions, the indexing of part of the extensions is missing.
+In this case, add the path to your extension in `.vscode/settings.json` under the key `"python.analysis.extraPaths"`.
+
+```json
+{
+    "python.analysis.extraPaths": [
+        "<path-to-ext-repo>/source/FLEXR_v0"
+    ]
+}
+```
+
+### Pylance Crash
+
+If you encounter a crash in `pylance`, it is probable that too many files are indexed and you run out of memory.
+A possible solution is to exclude some of omniverse packages that are not used in your project.
+To do so, modify `.vscode/settings.json` and comment out packages under the key `"python.analysis.extraPaths"`
+Some examples of packages that can likely be excluded are:
+
+```json
+"<path-to-isaac-sim>/extscache/omni.anim.*"         // Animation packages
+"<path-to-isaac-sim>/extscache/omni.kit.*"          // Kit UI tools
+"<path-to-isaac-sim>/extscache/omni.graph.*"        // Graph UI tools
+"<path-to-isaac-sim>/extscache/omni.services.*"     // Services tools
+...
+```
--- a/scripts/list_envs.py
+++ b/scripts/list_envs.py
@@ -0,0 +1,64 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""
+Script to print all the available environments in Isaac Lab.
+
+The script iterates over all registered environments and stores the details in a table.
+It prints the name of the environment, the entry point and the config file.
+
+All the environments are registered in the `FLEXR_v0` extension. They start
+with `Isaac` in their name.
+"""
+
+"""Launch Isaac Sim Simulator first."""
+
+from isaaclab.app import AppLauncher
+
+# launch omniverse app
+app_launcher = AppLauncher(headless=True)
+simulation_app = app_launcher.app
+
+
+"""Rest everything follows."""
+
+import gymnasium as gym
+from prettytable import PrettyTable
+
+import FLEXR_v0.tasks  # noqa: F401
+
+
+def main():
+    """Print all environments registered in `FLEXR_v0` extension."""
+    # print all the available environments
+    table = PrettyTable(["S. No.", "Task Name", "Entry Point", "Config"])
+    table.title = "Available Environments in Isaac Lab"
+    # set alignment of table columns
+    table.align["Task Name"] = "l"
+    table.align["Entry Point"] = "l"
+    table.align["Config"] = "l"
+
+    # count of environments
+    index = 0
+    # acquire all Isaac environments names
+    for task_spec in gym.registry.values():
+        if "Template-" in task_spec.id:
+            # add details to table
+            table.add_row([index + 1, task_spec.id, task_spec.entry_point, task_spec.kwargs["env_cfg_entry_point"]])
+            # increment count
+            index += 1
+
+    print(table)
+
+
+if __name__ == "__main__":
+    try:
+        # run the main function
+        main()
+    except Exception as e:
+        raise e
+    finally:
+        # close the app
+        simulation_app.close()
--- a/scripts/random_agent.py
+++ b/scripts/random_agent.py
@@ -0,0 +1,72 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Script to an environment with random action agent."""
+
+"""Launch Isaac Sim Simulator first."""
+
+import argparse
+
+from isaaclab.app import AppLauncher
+
+# add argparse arguments
+parser = argparse.ArgumentParser(description="Random agent for Isaac Lab environments.")
+parser.add_argument(
+    "--disable_fabric", action="store_true", default=False, help="Disable fabric and use USD I/O operations."
+)
+parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
+parser.add_argument("--task", type=str, default=None, help="Name of the task.")
+# append AppLauncher cli args
+AppLauncher.add_app_launcher_args(parser)
+# parse the arguments
+args_cli = parser.parse_args()
+
+# launch omniverse app
+app_launcher = AppLauncher(args_cli)
+simulation_app = app_launcher.app
+
+"""Rest everything follows."""
+
+import gymnasium as gym
+import torch
+
+import isaaclab_tasks  # noqa: F401
+from isaaclab_tasks.utils import parse_env_cfg
+
+import FLEXR_v0.tasks  # noqa: F401
+
+
+def main():
+    """Random actions agent with Isaac Lab environment."""
+    # create environment configuration
+    env_cfg = parse_env_cfg(
+        args_cli.task, device=args_cli.device, num_envs=args_cli.num_envs, use_fabric=not args_cli.disable_fabric
+    )
+    # create environment
+    env = gym.make(args_cli.task, cfg=env_cfg)
+
+    # print info (this is vectorized environment)
+    print(f"[INFO]: Gym observation space: {env.observation_space}")
+    print(f"[INFO]: Gym action space: {env.action_space}")
+    # reset environment
+    env.reset()
+    # simulate environment
+    while simulation_app.is_running():
+        # run everything in inference mode
+        with torch.inference_mode():
+            # sample actions from -1 to 1
+            actions = 2 * torch.rand(env.action_space.shape, device=env.unwrapped.device) - 1
+            # apply actions
+            env.step(actions)
+
+    # close the simulator
+    env.close()
+
+
+if __name__ == "__main__":
+    # run the main function
+    main()
+    # close sim app
+    simulation_app.close()
--- a/scripts/rl_games/play.py
+++ b/scripts/rl_games/play.py
@@ -0,0 +1,207 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Script to play a checkpoint if an RL agent from RL-Games."""
+
+"""Launch Isaac Sim Simulator first."""
+
+import argparse
+
+from isaaclab.app import AppLauncher
+
+# add argparse arguments
+parser = argparse.ArgumentParser(description="Play a checkpoint of an RL agent from RL-Games.")
+parser.add_argument("--video", action="store_true", default=False, help="Record videos during training.")
+parser.add_argument("--video_length", type=int, default=200, help="Length of the recorded video (in steps).")
+parser.add_argument(
+    "--disable_fabric", action="store_true", default=False, help="Disable fabric and use USD I/O operations."
+)
+parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
+parser.add_argument("--task", type=str, default=None, help="Name of the task.")
+parser.add_argument("--checkpoint", type=str, default=None, help="Path to model checkpoint.")
+parser.add_argument(
+    "--use_pretrained_checkpoint",
+    action="store_true",
+    help="Use the pre-trained checkpoint from Nucleus.",
+)
+parser.add_argument(
+    "--use_last_checkpoint",
+    action="store_true",
+    help="When no checkpoint provided, use the last saved model. Otherwise use the best saved model.",
+)
+parser.add_argument("--real-time", action="store_true", default=False, help="Run in real-time, if possible.")
+# append AppLauncher cli args
+AppLauncher.add_app_launcher_args(parser)
+# parse the arguments
+args_cli = parser.parse_args()
+# always enable cameras to record video
+if args_cli.video:
+    args_cli.enable_cameras = True
+
+# launch omniverse app
+app_launcher = AppLauncher(args_cli)
+simulation_app = app_launcher.app
+
+"""Rest everything follows."""
+
+
+import gymnasium as gym
+import math
+import os
+import time
+import torch
+
+from rl_games.common import env_configurations, vecenv
+from rl_games.common.player import BasePlayer
+from rl_games.torch_runner import Runner
+
+from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
+from isaaclab.utils.assets import retrieve_file_path
+from isaaclab.utils.dict import print_dict
+from isaaclab.utils.pretrained_checkpoint import get_published_pretrained_checkpoint
+
+from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
+
+import isaaclab_tasks  # noqa: F401
+from isaaclab_tasks.utils import get_checkpoint_path, load_cfg_from_registry, parse_env_cfg
+
+import FLEXR_v0.tasks  # noqa: F401
+
+
+def main():
+    """Play with RL-Games agent."""
+    # parse env configuration
+    env_cfg = parse_env_cfg(
+        args_cli.task, device=args_cli.device, num_envs=args_cli.num_envs, use_fabric=not args_cli.disable_fabric
+    )
+    agent_cfg = load_cfg_from_registry(args_cli.task, "rl_games_cfg_entry_point")
+
+    # specify directory for logging experiments
+    log_root_path = os.path.join("logs", "rl_games", agent_cfg["params"]["config"]["name"])
+    log_root_path = os.path.abspath(log_root_path)
+    print(f"[INFO] Loading experiment from directory: {log_root_path}")
+    # find checkpoint
+    if args_cli.use_pretrained_checkpoint:
+        resume_path = get_published_pretrained_checkpoint("rl_games", args_cli.task)
+        if not resume_path:
+            print("[INFO] Unfortunately a pre-trained checkpoint is currently unavailable for this task.")
+            return
+    elif args_cli.checkpoint is None:
+        # specify directory for logging runs
+        run_dir = agent_cfg["params"]["config"].get("full_experiment_name", ".*")
+        # specify name of checkpoint
+        if args_cli.use_last_checkpoint:
+            checkpoint_file = ".*"
+        else:
+            # this loads the best checkpoint
+            checkpoint_file = f"{agent_cfg['params']['config']['name']}.pth"
+        # get path to previous checkpoint
+        resume_path = get_checkpoint_path(log_root_path, run_dir, checkpoint_file, other_dirs=["nn"])
+    else:
+        resume_path = retrieve_file_path(args_cli.checkpoint)
+    log_dir = os.path.dirname(os.path.dirname(resume_path))
+
+    # wrap around environment for rl-games
+    rl_device = agent_cfg["params"]["config"]["device"]
+    clip_obs = agent_cfg["params"]["env"].get("clip_observations", math.inf)
+    clip_actions = agent_cfg["params"]["env"].get("clip_actions", math.inf)
+
+    # create isaac environment
+    env = gym.make(args_cli.task, cfg=env_cfg, render_mode="rgb_array" if args_cli.video else None)
+
+    # convert to single-agent instance if required by the RL algorithm
+    if isinstance(env.unwrapped, DirectMARLEnv):
+        env = multi_agent_to_single_agent(env)
+
+    # wrap for video recording
+    if args_cli.video:
+        video_kwargs = {
+            "video_folder": os.path.join(log_root_path, log_dir, "videos", "play"),
+            "step_trigger": lambda step: step == 0,
+            "video_length": args_cli.video_length,
+            "disable_logger": True,
+        }
+        print("[INFO] Recording videos during training.")
+        print_dict(video_kwargs, nesting=4)
+        env = gym.wrappers.RecordVideo(env, **video_kwargs)
+
+    # wrap around environment for rl-games
+    env = RlGamesVecEnvWrapper(env, rl_device, clip_obs, clip_actions)
+
+    # register the environment to rl-games registry
+    # note: in agents configuration: environment name must be "rlgpu"
+    vecenv.register(
+        "IsaacRlgWrapper", lambda config_name, num_actors, **kwargs: RlGamesGpuEnv(config_name, num_actors, **kwargs)
+    )
+    env_configurations.register("rlgpu", {"vecenv_type": "IsaacRlgWrapper", "env_creator": lambda **kwargs: env})
+
+    # load previously trained model
+    agent_cfg["params"]["load_checkpoint"] = True
+    agent_cfg["params"]["load_path"] = resume_path
+    print(f"[INFO]: Loading model checkpoint from: {agent_cfg['params']['load_path']}")
+
+    # set number of actors into agent config
+    agent_cfg["params"]["config"]["num_actors"] = env.unwrapped.num_envs
+    # create runner from rl-games
+    runner = Runner()
+    runner.load(agent_cfg)
+    # obtain the agent from the runner
+    agent: BasePlayer = runner.create_player()
+    agent.restore(resume_path)
+    agent.reset()
+
+    dt = env.unwrapped.step_dt
+
+    # reset environment
+    obs = env.reset()
+    if isinstance(obs, dict):
+        obs = obs["obs"]
+    timestep = 0
+    # required: enables the flag for batched observations
+    _ = agent.get_batch_size(obs, 1)
+    # initialize RNN states if used
+    if agent.is_rnn:
+        agent.init_rnn()
+    # simulate environment
+    # note: We simplified the logic in rl-games player.py (:func:`BasePlayer.run()`) function in an
+    #   attempt to have complete control over environment stepping. However, this removes other
+    #   operations such as masking that is used for multi-agent learning by RL-Games.
+    while simulation_app.is_running():
+        start_time = time.time()
+        # run everything in inference mode
+        with torch.inference_mode():
+            # convert obs to agent format
+            obs = agent.obs_to_torch(obs)
+            # agent stepping
+            actions = agent.get_action(obs, is_deterministic=agent.is_deterministic)
+            # env stepping
+            obs, _, dones, _ = env.step(actions)
+
+            # perform operations for terminated episodes
+            if len(dones) > 0:
+                # reset rnn state for terminated episodes
+                if agent.is_rnn and agent.states is not None:
+                    for s in agent.states:
+                        s[:, dones, :] = 0.0
+        if args_cli.video:
+            timestep += 1
+            # Exit the play loop after recording one video
+            if timestep == args_cli.video_length:
+                break
+
+        # time delay for real-time evaluation
+        sleep_time = dt - (time.time() - start_time)
+        if args_cli.real_time and sleep_time > 0:
+            time.sleep(sleep_time)
+
+    # close the simulator
+    env.close()
+
+
+if __name__ == "__main__":
+    # run the main function
+    main()
+    # close sim app
+    simulation_app.close()
--- a/scripts/rl_games/train.py
+++ b/scripts/rl_games/train.py
@@ -0,0 +1,184 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Script to train RL agent with RL-Games."""
+
+"""Launch Isaac Sim Simulator first."""
+
+import argparse
+import sys
+
+from isaaclab.app import AppLauncher
+
+# add argparse arguments
+parser = argparse.ArgumentParser(description="Train an RL agent with RL-Games.")
+parser.add_argument("--video", action="store_true", default=False, help="Record videos during training.")
+parser.add_argument("--video_length", type=int, default=200, help="Length of the recorded video (in steps).")
+parser.add_argument("--video_interval", type=int, default=2000, help="Interval between video recordings (in steps).")
+parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
+parser.add_argument("--task", type=str, default=None, help="Name of the task.")
+parser.add_argument("--seed", type=int, default=None, help="Seed used for the environment")
+parser.add_argument(
+    "--distributed", action="store_true", default=False, help="Run training with multiple GPUs or nodes."
+)
+parser.add_argument("--checkpoint", type=str, default=None, help="Path to model checkpoint.")
+parser.add_argument("--sigma", type=str, default=None, help="The policy's initial standard deviation.")
+parser.add_argument("--max_iterations", type=int, default=None, help="RL Policy training iterations.")
+
+# append AppLauncher cli args
+AppLauncher.add_app_launcher_args(parser)
+# parse the arguments
+args_cli, hydra_args = parser.parse_known_args()
+# always enable cameras to record video
+if args_cli.video:
+    args_cli.enable_cameras = True
+
+# clear out sys.argv for Hydra
+sys.argv = [sys.argv[0]] + hydra_args
+
+# launch omniverse app
+app_launcher = AppLauncher(args_cli)
+simulation_app = app_launcher.app
+
+"""Rest everything follows."""
+
+import gymnasium as gym
+import math
+import os
+import random
+from datetime import datetime
+
+from rl_games.common import env_configurations, vecenv
+from rl_games.common.algo_observer import IsaacAlgoObserver
+from rl_games.torch_runner import Runner
+
+from isaaclab.envs import (
+    DirectMARLEnv,
+    DirectMARLEnvCfg,
+    DirectRLEnvCfg,
+    ManagerBasedRLEnvCfg,
+    multi_agent_to_single_agent,
+)
+from isaaclab.utils.assets import retrieve_file_path
+from isaaclab.utils.dict import print_dict
+from isaaclab.utils.io import dump_pickle, dump_yaml
+
+from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
+
+import isaaclab_tasks  # noqa: F401
+from isaaclab_tasks.utils.hydra import hydra_task_config
+
+import FLEXR_v0.tasks  # noqa: F401
+
+
+@hydra_task_config(args_cli.task, "rl_games_cfg_entry_point")
+def main(env_cfg: ManagerBasedRLEnvCfg | DirectRLEnvCfg | DirectMARLEnvCfg, agent_cfg: dict):
+    """Train with RL-Games agent."""
+    # override configurations with non-hydra CLI arguments
+    env_cfg.scene.num_envs = args_cli.num_envs if args_cli.num_envs is not None else env_cfg.scene.num_envs
+    env_cfg.sim.device = args_cli.device if args_cli.device is not None else env_cfg.sim.device
+
+    # randomly sample a seed if seed = -1
+    if args_cli.seed == -1:
+        args_cli.seed = random.randint(0, 10000)
+
+    agent_cfg["params"]["seed"] = args_cli.seed if args_cli.seed is not None else agent_cfg["params"]["seed"]
+    agent_cfg["params"]["config"]["max_epochs"] = (
+        args_cli.max_iterations if args_cli.max_iterations is not None else agent_cfg["params"]["config"]["max_epochs"]
+    )
+    if args_cli.checkpoint is not None:
+        resume_path = retrieve_file_path(args_cli.checkpoint)
+        agent_cfg["params"]["load_checkpoint"] = True
+        agent_cfg["params"]["load_path"] = resume_path
+        print(f"[INFO]: Loading model checkpoint from: {agent_cfg['params']['load_path']}")
+    train_sigma = float(args_cli.sigma) if args_cli.sigma is not None else None
+
+    # multi-gpu training config
+    if args_cli.distributed:
+        agent_cfg["params"]["seed"] += app_launcher.global_rank
+        agent_cfg["params"]["config"]["device"] = f"cuda:{app_launcher.local_rank}"
+        agent_cfg["params"]["config"]["device_name"] = f"cuda:{app_launcher.local_rank}"
+        agent_cfg["params"]["config"]["multi_gpu"] = True
+        # update env config device
+        env_cfg.sim.device = f"cuda:{app_launcher.local_rank}"
+
+    # set the environment seed (after multi-gpu config for updated rank from agent seed)
+    # note: certain randomizations occur in the environment initialization so we set the seed here
+    env_cfg.seed = agent_cfg["params"]["seed"]
+
+    # specify directory for logging experiments
+    log_root_path = os.path.join("logs", "rl_games", agent_cfg["params"]["config"]["name"])
+    log_root_path = os.path.abspath(log_root_path)
+    print(f"[INFO] Logging experiment in directory: {log_root_path}")
+    # specify directory for logging runs
+    log_dir = agent_cfg["params"]["config"].get("full_experiment_name", datetime.now().strftime("%Y-%m-%d_%H-%M-%S"))
+    # set directory into agent config
+    # logging directory path: <train_dir>/<full_experiment_name>
+    agent_cfg["params"]["config"]["train_dir"] = log_root_path
+    agent_cfg["params"]["config"]["full_experiment_name"] = log_dir
+
+    # dump the configuration into log-directory
+    dump_yaml(os.path.join(log_root_path, log_dir, "params", "env.yaml"), env_cfg)
+    dump_yaml(os.path.join(log_root_path, log_dir, "params", "agent.yaml"), agent_cfg)
+    dump_pickle(os.path.join(log_root_path, log_dir, "params", "env.pkl"), env_cfg)
+    dump_pickle(os.path.join(log_root_path, log_dir, "params", "agent.pkl"), agent_cfg)
+
+    # read configurations about the agent-training
+    rl_device = agent_cfg["params"]["config"]["device"]
+    clip_obs = agent_cfg["params"]["env"].get("clip_observations", math.inf)
+    clip_actions = agent_cfg["params"]["env"].get("clip_actions", math.inf)
+
+    # create isaac environment
+    env = gym.make(args_cli.task, cfg=env_cfg, render_mode="rgb_array" if args_cli.video else None)
+
+    # convert to single-agent instance if required by the RL algorithm
+    if isinstance(env.unwrapped, DirectMARLEnv):
+        env = multi_agent_to_single_agent(env)
+
+    # wrap for video recording
+    if args_cli.video:
+        video_kwargs = {
+            "video_folder": os.path.join(log_root_path, log_dir, "videos", "train"),
+            "step_trigger": lambda step: step % args_cli.video_interval == 0,
+            "video_length": args_cli.video_length,
+            "disable_logger": True,
+        }
+        print("[INFO] Recording videos during training.")
+        print_dict(video_kwargs, nesting=4)
+        env = gym.wrappers.RecordVideo(env, **video_kwargs)
+
+    # wrap around environment for rl-games
+    env = RlGamesVecEnvWrapper(env, rl_device, clip_obs, clip_actions)
+
+    # register the environment to rl-games registry
+    # note: in agents configuration: environment name must be "rlgpu"
+    vecenv.register(
+        "IsaacRlgWrapper", lambda config_name, num_actors, **kwargs: RlGamesGpuEnv(config_name, num_actors, **kwargs)
+    )
+    env_configurations.register("rlgpu", {"vecenv_type": "IsaacRlgWrapper", "env_creator": lambda **kwargs: env})
+
+    # set number of actors into agent config
+    agent_cfg["params"]["config"]["num_actors"] = env.unwrapped.num_envs
+    # create runner from rl-games
+    runner = Runner(IsaacAlgoObserver())
+    runner.load(agent_cfg)
+
+    # reset the agent and env
+    runner.reset()
+    # train the agent
+    if args_cli.checkpoint is not None:
+        runner.run({"train": True, "play": False, "sigma": train_sigma, "checkpoint": resume_path})
+    else:
+        runner.run({"train": True, "play": False, "sigma": train_sigma})
+
+    # close the simulator
+    env.close()
+
+
+if __name__ == "__main__":
+    # run the main function
+    main()
+    # close sim app
+    simulation_app.close()
--- a/scripts/rsl_rl/pycache/cli_args.cpython-310.pyc
+++ b/scripts/rsl_rl/pycache/cli_args.cpython-310.pyc
--- a/scripts/rsl_rl/cli_args.py
+++ b/scripts/rsl_rl/cli_args.py
@@ -0,0 +1,91 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+from __future__ import annotations
+
+import argparse
+import random
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg
+
+
+def add_rsl_rl_args(parser: argparse.ArgumentParser):
+    """Add RSL-RL arguments to the parser.
+
+    Args:
+        parser: The parser to add the arguments to.
+    """
+    # create a new argument group
+    arg_group = parser.add_argument_group("rsl_rl", description="Arguments for RSL-RL agent.")
+    # -- experiment arguments
+    arg_group.add_argument(
+        "--experiment_name", type=str, default=None, help="Name of the experiment folder where logs will be stored."
+    )
+    arg_group.add_argument("--run_name", type=str, default=None, help="Run name suffix to the log directory.")
+    # -- load arguments
+    arg_group.add_argument("--resume", action="store_true", default=False, help="Whether to resume from a checkpoint.")
+    arg_group.add_argument("--load_run", type=str, default=None, help="Name of the run folder to resume from.")
+    arg_group.add_argument("--checkpoint", type=str, default=None, help="Checkpoint file to resume from.")
+    # -- logger arguments
+    arg_group.add_argument(
+        "--logger", type=str, default=None, choices={"wandb", "tensorboard", "neptune"}, help="Logger module to use."
+    )
+    arg_group.add_argument(
+        "--log_project_name", type=str, default=None, help="Name of the logging project when using wandb or neptune."
+    )
+
+
+def parse_rsl_rl_cfg(task_name: str, args_cli: argparse.Namespace) -> RslRlOnPolicyRunnerCfg:
+    """Parse configuration for RSL-RL agent based on inputs.
+
+    Args:
+        task_name: The name of the environment.
+        args_cli: The command line arguments.
+
+    Returns:
+        The parsed configuration for RSL-RL agent based on inputs.
+    """
+    from isaaclab_tasks.utils.parse_cfg import load_cfg_from_registry
+
+    # load the default configuration
+    rslrl_cfg: RslRlOnPolicyRunnerCfg = load_cfg_from_registry(task_name, "rsl_rl_cfg_entry_point")
+    rslrl_cfg = update_rsl_rl_cfg(rslrl_cfg, args_cli)
+    return rslrl_cfg
+
+
+def update_rsl_rl_cfg(agent_cfg: RslRlOnPolicyRunnerCfg, args_cli: argparse.Namespace):
+    """Update configuration for RSL-RL agent based on inputs.
+
+    Args:
+        agent_cfg: The configuration for RSL-RL agent.
+        args_cli: The command line arguments.
+
+    Returns:
+        The updated configuration for RSL-RL agent based on inputs.
+    """
+    # override the default configuration with CLI arguments
+    if hasattr(args_cli, "seed") and args_cli.seed is not None:
+        # randomly sample a seed if seed = -1
+        if args_cli.seed == -1:
+            args_cli.seed = random.randint(0, 10000)
+        agent_cfg.seed = args_cli.seed
+    if args_cli.resume is not None:
+        agent_cfg.resume = args_cli.resume
+    if args_cli.load_run is not None:
+        agent_cfg.load_run = args_cli.load_run
+    if args_cli.checkpoint is not None:
+        agent_cfg.load_checkpoint = args_cli.checkpoint
+    if args_cli.run_name is not None:
+        agent_cfg.run_name = args_cli.run_name
+    if args_cli.logger is not None:
+        agent_cfg.logger = args_cli.logger
+    # set the project name for wandb and neptune
+    if agent_cfg.logger in {"wandb", "neptune"} and args_cli.log_project_name:
+        agent_cfg.wandb_project = args_cli.log_project_name
+        agent_cfg.neptune_project = args_cli.log_project_name
+
+    return agent_cfg
--- a/scripts/rsl_rl/play.py
+++ b/scripts/rsl_rl/play.py
@@ -0,0 +1,170 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Script to play a checkpoint if an RL agent from RSL-RL."""
+
+"""Launch Isaac Sim Simulator first."""
+
+import argparse
+
+from isaaclab.app import AppLauncher
+
+# local imports
+import cli_args  # isort: skip
+
+# add argparse arguments
+parser = argparse.ArgumentParser(description="Train an RL agent with RSL-RL.")
+parser.add_argument("--video", action="store_true", default=False, help="Record videos during training.")
+parser.add_argument("--video_length", type=int, default=200, help="Length of the recorded video (in steps).")
+parser.add_argument(
+    "--disable_fabric", action="store_true", default=False, help="Disable fabric and use USD I/O operations."
+)
+parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
+parser.add_argument("--task", type=str, default=None, help="Name of the task.")
+parser.add_argument(
+    "--use_pretrained_checkpoint",
+    action="store_true",
+    help="Use the pre-trained checkpoint from Nucleus.",
+)
+parser.add_argument("--real-time", action="store_true", default=False, help="Run in real-time, if possible.")
+# append RSL-RL cli arguments
+cli_args.add_rsl_rl_args(parser)
+# append AppLauncher cli args
+AppLauncher.add_app_launcher_args(parser)
+args_cli = parser.parse_args()
+# always enable cameras to record video
+if args_cli.video:
+    args_cli.enable_cameras = True
+
+# launch omniverse app
+app_launcher = AppLauncher(args_cli)
+simulation_app = app_launcher.app
+
+"""Rest everything follows."""
+
+import gymnasium as gym
+import os
+import time
+import torch
+
+from rsl_rl.runners import OnPolicyRunner
+
+from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
+from isaaclab.utils.assets import retrieve_file_path
+from isaaclab.utils.dict import print_dict
+from isaaclab.utils.pretrained_checkpoint import get_published_pretrained_checkpoint
+
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper, export_policy_as_jit, export_policy_as_onnx
+
+import isaaclab_tasks  # noqa: F401
+from isaaclab_tasks.utils import get_checkpoint_path, parse_env_cfg
+
+import FLEXR_v0.tasks  # noqa: F401
+
+
+def main():
+    """Play with RSL-RL agent."""
+    # parse configuration
+    env_cfg = parse_env_cfg(
+        args_cli.task, device=args_cli.device, num_envs=args_cli.num_envs, use_fabric=not args_cli.disable_fabric
+    )
+    agent_cfg: RslRlOnPolicyRunnerCfg = cli_args.parse_rsl_rl_cfg(args_cli.task, args_cli)
+
+    # specify directory for logging experiments
+    log_root_path = os.path.join("logs", "rsl_rl", agent_cfg.experiment_name)
+    log_root_path = os.path.abspath(log_root_path)
+    print(f"[INFO] Loading experiment from directory: {log_root_path}")
+    if args_cli.use_pretrained_checkpoint:
+        resume_path = get_published_pretrained_checkpoint("rsl_rl", args_cli.task)
+        if not resume_path:
+            print("[INFO] Unfortunately a pre-trained checkpoint is currently unavailable for this task.")
+            return
+    elif args_cli.checkpoint:
+        resume_path = retrieve_file_path(args_cli.checkpoint)
+    else:
+        resume_path = get_checkpoint_path(log_root_path, agent_cfg.load_run, agent_cfg.load_checkpoint)
+
+    log_dir = os.path.dirname(resume_path)
+
+    # create isaac environment
+    env = gym.make(args_cli.task, cfg=env_cfg, render_mode="rgb_array" if args_cli.video else None)
+
+    # convert to single-agent instance if required by the RL algorithm
+    if isinstance(env.unwrapped, DirectMARLEnv):
+        env = multi_agent_to_single_agent(env)
+
+    # wrap for video recording
+    if args_cli.video:
+        video_kwargs = {
+            "video_folder": os.path.join(log_dir, "videos", "play"),
+            "step_trigger": lambda step: step == 0,
+            "video_length": args_cli.video_length,
+            "disable_logger": True,
+        }
+        print("[INFO] Recording videos during training.")
+        print_dict(video_kwargs, nesting=4)
+        env = gym.wrappers.RecordVideo(env, **video_kwargs)
+
+    # wrap around environment for rsl-rl
+    env = RslRlVecEnvWrapper(env, clip_actions=agent_cfg.clip_actions)
+
+    print(f"[INFO]: Loading model checkpoint from: {resume_path}")
+    # load previously trained model
+    ppo_runner = OnPolicyRunner(env, agent_cfg.to_dict(), log_dir=None, device=agent_cfg.device)
+    ppo_runner.load(resume_path)
+
+    # obtain the trained policy for inference
+    policy = ppo_runner.get_inference_policy(device=env.unwrapped.device)
+
+    # extract the neural network module
+    # we do this in a try-except to maintain backwards compatibility.
+    try:
+        # version 2.3 onwards
+        policy_nn = ppo_runner.alg.policy
+    except AttributeError:
+        # version 2.2 and below
+        policy_nn = ppo_runner.alg.actor_critic
+
+    # export policy to onnx/jit
+    export_model_dir = os.path.join(os.path.dirname(resume_path), "exported")
+    export_policy_as_jit(policy_nn, ppo_runner.obs_normalizer, path=export_model_dir, filename="policy.pt")
+    export_policy_as_onnx(
+        policy_nn, normalizer=ppo_runner.obs_normalizer, path=export_model_dir, filename="policy.onnx"
+    )
+
+    dt = env.unwrapped.step_dt
+
+    # reset environment
+    obs, _ = env.get_observations()
+    timestep = 0
+    # simulate environment
+    while simulation_app.is_running():
+        start_time = time.time()
+        # run everything in inference mode
+        with torch.inference_mode():
+            # agent stepping
+            actions = policy(obs)
+            # env stepping
+            obs, _, _, _ = env.step(actions)
+        if args_cli.video:
+            timestep += 1
+            # Exit the play loop after recording one video
+            if timestep == args_cli.video_length:
+                break
+
+        # time delay for real-time evaluation
+        sleep_time = dt - (time.time() - start_time)
+        if args_cli.real_time and sleep_time > 0:
+            time.sleep(sleep_time)
+
+    # close the simulator
+    env.close()
+
+
+if __name__ == "__main__":
+    # run the main function
+    main()
+    # close sim app
+    simulation_app.close()
--- a/scripts/rsl_rl/train.py
+++ b/scripts/rsl_rl/train.py
@@ -0,0 +1,193 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Script to train RL agent with RSL-RL."""
+
+"""Launch Isaac Sim Simulator first."""
+
+import argparse
+import sys
+
+from isaaclab.app import AppLauncher
+
+# local imports
+import cli_args  # isort: skip
+
+
+# add argparse arguments
+parser = argparse.ArgumentParser(description="Train an RL agent with RSL-RL.")
+parser.add_argument("--video", action="store_true", default=False, help="Record videos during training.")
+parser.add_argument("--video_length", type=int, default=200, help="Length of the recorded video (in steps).")
+parser.add_argument("--video_interval", type=int, default=2000, help="Interval between video recordings (in steps).")
+parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
+parser.add_argument("--task", type=str, default=None, help="Name of the task.")
+parser.add_argument("--seed", type=int, default=None, help="Seed used for the environment")
+parser.add_argument("--max_iterations", type=int, default=None, help="RL Policy training iterations.")
+parser.add_argument(
+    "--distributed", action="store_true", default=False, help="Run training with multiple GPUs or nodes."
+)
+# append RSL-RL cli arguments
+cli_args.add_rsl_rl_args(parser)
+# append AppLauncher cli args
+AppLauncher.add_app_launcher_args(parser)
+args_cli, hydra_args = parser.parse_known_args()
+
+# always enable cameras to record video
+if args_cli.video:
+    args_cli.enable_cameras = True
+
+# clear out sys.argv for Hydra
+sys.argv = [sys.argv[0]] + hydra_args
+
+# launch omniverse app
+app_launcher = AppLauncher(args_cli)
+simulation_app = app_launcher.app
+
+"""Check for minimum supported RSL-RL version."""
+
+import importlib.metadata as metadata
+import platform
+
+from packaging import version
+
+# for distributed training, check minimum supported rsl-rl version
+RSL_RL_VERSION = "2.3.1"
+installed_version = metadata.version("rsl-rl-lib")
+if args_cli.distributed and version.parse(installed_version) < version.parse(RSL_RL_VERSION):
+    if platform.system() == "Windows":
+        cmd = [r".\isaaclab.bat", "-p", "-m", "pip", "install", f"rsl-rl-lib=={RSL_RL_VERSION}"]
+    else:
+        cmd = ["./isaaclab.sh", "-p", "-m", "pip", "install", f"rsl-rl-lib=={RSL_RL_VERSION}"]
+    print(
+        f"Please install the correct version of RSL-RL.\nExisting version is: '{installed_version}'"
+        f" and required version is: '{RSL_RL_VERSION}'.\nTo install the correct version, run:"
+        f"\n\n\t{' '.join(cmd)}\n"
+    )
+    exit(1)
+
+"""Rest everything follows."""
+
+import gymnasium as gym
+import os
+import torch
+from datetime import datetime
+
+from rsl_rl.runners import OnPolicyRunner
+
+from isaaclab.envs import (
+    DirectMARLEnv,
+    DirectMARLEnvCfg,
+    DirectRLEnvCfg,
+    ManagerBasedRLEnvCfg,
+    multi_agent_to_single_agent,
+)
+from isaaclab.utils.dict import print_dict
+from isaaclab.utils.io import dump_pickle, dump_yaml
+
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper
+
+import isaaclab_tasks  # noqa: F401
+from isaaclab_tasks.utils import get_checkpoint_path
+from isaaclab_tasks.utils.hydra import hydra_task_config
+
+import FLEXR_v0.tasks  # noqa: F401
+
+torch.backends.cuda.matmul.allow_tf32 = True
+torch.backends.cudnn.allow_tf32 = True
+torch.backends.cudnn.deterministic = False
+torch.backends.cudnn.benchmark = False
+
+
+@hydra_task_config(args_cli.task, "rsl_rl_cfg_entry_point")
+def main(env_cfg: ManagerBasedRLEnvCfg | DirectRLEnvCfg | DirectMARLEnvCfg, agent_cfg: RslRlOnPolicyRunnerCfg):
+    """Train with RSL-RL agent."""
+    # override configurations with non-hydra CLI arguments
+    agent_cfg = cli_args.update_rsl_rl_cfg(agent_cfg, args_cli)
+    env_cfg.scene.num_envs = args_cli.num_envs if args_cli.num_envs is not None else env_cfg.scene.num_envs
+    agent_cfg.max_iterations = (
+        args_cli.max_iterations if args_cli.max_iterations is not None else agent_cfg.max_iterations
+    )
+
+    # set the environment seed
+    # note: certain randomizations occur in the environment initialization so we set the seed here
+    env_cfg.seed = agent_cfg.seed
+    env_cfg.sim.device = args_cli.device if args_cli.device is not None else env_cfg.sim.device
+
+    # multi-gpu training configuration
+    if args_cli.distributed:
+        env_cfg.sim.device = f"cuda:{app_launcher.local_rank}"
+        agent_cfg.device = f"cuda:{app_launcher.local_rank}"
+
+        # set seed to have diversity in different threads
+        seed = agent_cfg.seed + app_launcher.local_rank
+        env_cfg.seed = seed
+        agent_cfg.seed = seed
+
+    # specify directory for logging experiments
+    log_root_path = os.path.join("logs", "rsl_rl", agent_cfg.experiment_name)
+    log_root_path = os.path.abspath(log_root_path)
+    print(f"[INFO] Logging experiment in directory: {log_root_path}")
+    # specify directory for logging runs: {time-stamp}_{run_name}
+    log_dir = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+    # The Ray Tune workflow extracts experiment name using the logging line below, hence, do not change it (see PR #2346, comment-2819298849)
+    print(f"Exact experiment name requested from command line: {log_dir}")
+    if agent_cfg.run_name:
+        log_dir += f"_{agent_cfg.run_name}"
+    log_dir = os.path.join(log_root_path, log_dir)
+
+    # create isaac environment
+    env = gym.make(args_cli.task, cfg=env_cfg, render_mode="rgb_array" if args_cli.video else None)
+
+    # convert to single-agent instance if required by the RL algorithm
+    if isinstance(env.unwrapped, DirectMARLEnv):
+        env = multi_agent_to_single_agent(env)
+
+    # save resume path before creating a new log_dir
+    if agent_cfg.resume or agent_cfg.algorithm.class_name == "Distillation":
+        resume_path = get_checkpoint_path(log_root_path, agent_cfg.load_run, agent_cfg.load_checkpoint)
+
+    # wrap for video recording
+    if args_cli.video:
+        video_kwargs = {
+            "video_folder": os.path.join(log_dir, "videos", "train"),
+            "step_trigger": lambda step: step % args_cli.video_interval == 0,
+            "video_length": args_cli.video_length,
+            "disable_logger": True,
+        }
+        print("[INFO] Recording videos during training.")
+        print_dict(video_kwargs, nesting=4)
+        env = gym.wrappers.RecordVideo(env, **video_kwargs)
+
+    # wrap around environment for rsl-rl
+    env = RslRlVecEnvWrapper(env, clip_actions=agent_cfg.clip_actions)
+
+    # create runner from rsl-rl
+    runner = OnPolicyRunner(env, agent_cfg.to_dict(), log_dir=log_dir, device=agent_cfg.device)
+    # write git state to logs
+    runner.add_git_repo_to_log(__file__)
+    # load the checkpoint
+    if agent_cfg.resume or agent_cfg.algorithm.class_name == "Distillation":
+        print(f"[INFO]: Loading model checkpoint from: {resume_path}")
+        # load previously trained model
+        runner.load(resume_path)
+
+    # dump the configuration into log-directory
+    dump_yaml(os.path.join(log_dir, "params", "env.yaml"), env_cfg)
+    dump_yaml(os.path.join(log_dir, "params", "agent.yaml"), agent_cfg)
+    dump_pickle(os.path.join(log_dir, "params", "env.pkl"), env_cfg)
+    dump_pickle(os.path.join(log_dir, "params", "agent.pkl"), agent_cfg)
+
+    # run training
+    runner.learn(num_learning_iterations=agent_cfg.max_iterations, init_at_random_ep_len=True)
+
+    # close the simulator
+    env.close()
+
+
+if __name__ == "__main__":
+    # run the main function
+    main()
+    # close sim app
+    simulation_app.close()
--- a/scripts/zero_agent.py
+++ b/scripts/zero_agent.py
@@ -0,0 +1,72 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Script to run an environment with zero action agent."""
+
+"""Launch Isaac Sim Simulator first."""
+
+import argparse
+
+from isaaclab.app import AppLauncher
+
+# add argparse arguments
+parser = argparse.ArgumentParser(description="Zero agent for Isaac Lab environments.")
+parser.add_argument(
+    "--disable_fabric", action="store_true", default=False, help="Disable fabric and use USD I/O operations."
+)
+parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
+parser.add_argument("--task", type=str, default=None, help="Name of the task.")
+# append AppLauncher cli args
+AppLauncher.add_app_launcher_args(parser)
+# parse the arguments
+args_cli = parser.parse_args()
+
+# launch omniverse app
+app_launcher = AppLauncher(args_cli)
+simulation_app = app_launcher.app
+
+"""Rest everything follows."""
+
+import gymnasium as gym
+import torch
+
+import isaaclab_tasks  # noqa: F401
+from isaaclab_tasks.utils import parse_env_cfg
+
+import FLEXR_v0.tasks  # noqa: F401
+
+
+def main():
+    """Zero actions agent with Isaac Lab environment."""
+    # parse configuration
+    env_cfg = parse_env_cfg(
+        args_cli.task, device=args_cli.device, num_envs=args_cli.num_envs, use_fabric=not args_cli.disable_fabric
+    )
+    # create environment
+    env = gym.make(args_cli.task, cfg=env_cfg)
+
+    # print info (this is vectorized environment)
+    print(f"[INFO]: Gym observation space: {env.observation_space}")
+    print(f"[INFO]: Gym action space: {env.action_space}")
+    # reset environment
+    env.reset()
+    # simulate environment
+    while simulation_app.is_running():
+        # run everything in inference mode
+        with torch.inference_mode():
+            # compute zero actions
+            actions = torch.zeros(env.action_space.shape, device=env.unwrapped.device)
+            # apply actions
+            env.step(actions)
+
+    # close the simulator
+    env.close()
+
+
+if __name__ == "__main__":
+    # run the main function
+    main()
+    # close sim app
+    simulation_app.close()
--- a/source/FLEXR_v0/FLEXR_v0/init.py
+++ b/source/FLEXR_v0/FLEXR_v0/init.py
@@ -0,0 +1,14 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""
+Python module serving as a project/extension template.
+"""
+
+# Register Gym environments.
+from .tasks import *
+
+# Register UI extensions.
+from .ui_extension_example import *
--- a/source/FLEXR_v0/FLEXR_v0/tasks/init.py
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/init.py
@@ -0,0 +1,17 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Package containing task implementations for the extension."""
+
+##
+# Register Gym environments.
+##
+
+from isaaclab_tasks.utils import import_packages
+
+# The blacklist is used to prevent importing configs from sub-packages
+_BLACKLIST_PKGS = ["utils", ".mdp"]
+# Import all configs in this package
+import_packages(__name__, _BLACKLIST_PKGS)
--- a/source/FLEXR_v0/FLEXR_v0/tasks/direct/init.py
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/direct/init.py
@@ -0,0 +1,6 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+import gymnasium as gym  # noqa: F401
--- a/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/init.py
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/init.py
@@ -0,0 +1,24 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+import gymnasium as gym
+
+from . import agents
+
+##
+# Register Gym environments.
+##
+
+
+gym.register(
+    id="Template-Flexr-V0-Direct-v0",
+    entry_point=f"{__name__}.flexr_v0_env:FlexrV0Env",
+    disable_env_checker=True,
+    kwargs={
+        "env_cfg_entry_point": f"{__name__}.flexr_v0_env_cfg:FlexrV0EnvCfg",
+        "rl_games_cfg_entry_point": f"{agents.__name__}:rl_games_ppo_cfg.yaml",
+        "rsl_rl_cfg_entry_point": f"{agents.__name__}.rsl_rl_ppo_cfg:PPORunnerCfg",
+    },
+)
--- a/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/agents/init.py
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/agents/init.py
@@ -0,0 +1,4 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
--- a/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/agents/rl_games_ppo_cfg.yaml
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/agents/rl_games_ppo_cfg.yaml
@@ -0,0 +1,78 @@
+params:
+  seed: 42
+
+  # environment wrapper clipping
+  env:
+    # added to the wrapper
+    clip_observations: 5.0
+    # can make custom wrapper?
+    clip_actions: 1.0
+
+  algo:
+    name: a2c_continuous
+
+  model:
+    name: continuous_a2c_logstd
+
+  # doesn't have this fine grained control but made it close
+  network:
+    name: actor_critic
+    separate: False
+    space:
+      continuous:
+        mu_activation: None
+        sigma_activation: None
+
+        mu_init:
+          name: default
+        sigma_init:
+          name: const_initializer
+          val: 0
+        fixed_sigma: True
+    mlp:
+      units: [32, 32]
+      activation: elu
+      d2rl: False
+
+      initializer:
+        name: default
+      regularizer:
+        name: None
+
+  load_checkpoint: False # flag which sets whether to load the checkpoint
+  load_path: '' # path to the checkpoint to load
+
+  config:
+    name: cartpole_direct
+    env_name: rlgpu
+    device: 'cuda:0'
+    device_name: 'cuda:0'
+    multi_gpu: False
+    ppo: True
+    mixed_precision: False
+    normalize_input: True
+    normalize_value: True
+    num_actors: -1  # configured from the script (based on num_envs)
+    reward_shaper:
+      scale_value: 0.1
+    normalize_advantage: True
+    gamma: 0.99
+    tau : 0.95
+    learning_rate: 5e-4
+    lr_schedule: adaptive
+    kl_threshold: 0.008
+    score_to_win: 20000
+    max_epochs: 150
+    save_best_after: 50
+    save_frequency: 25
+    grad_norm: 1.0
+    entropy_coef: 0.0
+    truncate_grads: True
+    e_clip: 0.2
+    horizon_length: 32
+    minibatch_size: 16384
+    mini_epochs: 8
+    critic_coef: 4
+    clip_value: True
+    seq_length: 4
+    bounds_loss_coef: 0.0001
--- a/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/agents/rsl_rl_ppo_cfg.py
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/agents/rsl_rl_ppo_cfg.py
@@ -0,0 +1,37 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+from isaaclab.utils import configclass
+
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
+
+@configclass
+class PPORunnerCfg(RslRlOnPolicyRunnerCfg):
+    num_steps_per_env = 16
+    max_iterations = 150
+    save_interval = 50
+    experiment_name = "cartpole_direct"
+    empirical_normalization = False
+    policy = RslRlPpoActorCriticCfg(
+        init_noise_std=1.0,
+        actor_hidden_dims=[32, 32],
+        critic_hidden_dims=[32, 32],
+        activation="elu",
+    )
+    algorithm = RslRlPpoAlgorithmCfg(
+        value_loss_coef=1.0,
+        use_clipped_value_loss=True,
+        clip_param=0.2,
+        entropy_coef=0.005,
+        num_learning_epochs=5,
+        num_mini_batches=4,
+        learning_rate=1.0e-3,
+        schedule="adaptive",
+        gamma=0.99,
+        lam=0.95,
+        desired_kl=0.01,
+        max_grad_norm=1.0,
+    )
--- a/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/flexr_v0_env.py
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/flexr_v0_env.py
@@ -0,0 +1,132 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+from __future__ import annotations
+
+import math
+import torch
+from collections.abc import Sequence
+
+import isaaclab.sim as sim_utils
+from isaaclab.assets import Articulation
+from isaaclab.envs import DirectRLEnv
+from isaaclab.sim.spawners.from_files import GroundPlaneCfg, spawn_ground_plane
+from isaaclab.utils.math import sample_uniform
+
+from .flexr_v0_env_cfg import FlexrV0EnvCfg
+
+
+class FlexrV0Env(DirectRLEnv):
+    cfg: FlexrV0EnvCfg
+
+    def __init__(self, cfg: FlexrV0EnvCfg, render_mode: str | None = None, **kwargs):
+        super().__init__(cfg, render_mode, **kwargs)
+
+        self._cart_dof_idx, _ = self.robot.find_joints(self.cfg.cart_dof_name)
+        self._pole_dof_idx, _ = self.robot.find_joints(self.cfg.pole_dof_name)
+
+        self.joint_pos = self.robot.data.joint_pos
+        self.joint_vel = self.robot.data.joint_vel
+
+    def _setup_scene(self):
+        self.robot = Articulation(self.cfg.robot_cfg)
+        # add ground plane
+        spawn_ground_plane(prim_path="/World/ground", cfg=GroundPlaneCfg())
+        # clone and replicate
+        self.scene.clone_environments(copy_from_source=False)
+        # add articulation to scene
+        self.scene.articulations["robot"] = self.robot
+        # add lights
+        light_cfg = sim_utils.DomeLightCfg(intensity=2000.0, color=(0.75, 0.75, 0.75))
+        light_cfg.func("/World/Light", light_cfg)
+
+    def _pre_physics_step(self, actions: torch.Tensor) -> None:
+        self.actions = actions.clone()
+
+    def _apply_action(self) -> None:
+        self.robot.set_joint_effort_target(self.actions * self.cfg.action_scale, joint_ids=self._cart_dof_idx)
+
+    def _get_observations(self) -> dict:
+        obs = torch.cat(
+            (
+                self.joint_pos[:, self._pole_dof_idx[0]].unsqueeze(dim=1),
+                self.joint_vel[:, self._pole_dof_idx[0]].unsqueeze(dim=1),
+                self.joint_pos[:, self._cart_dof_idx[0]].unsqueeze(dim=1),
+                self.joint_vel[:, self._cart_dof_idx[0]].unsqueeze(dim=1),
+            ),
+            dim=-1,
+        )
+        observations = {"policy": obs}
+        return observations
+
+    def _get_rewards(self) -> torch.Tensor:
+        total_reward = compute_rewards(
+            self.cfg.rew_scale_alive,
+            self.cfg.rew_scale_terminated,
+            self.cfg.rew_scale_pole_pos,
+            self.cfg.rew_scale_cart_vel,
+            self.cfg.rew_scale_pole_vel,
+            self.joint_pos[:, self._pole_dof_idx[0]],
+            self.joint_vel[:, self._pole_dof_idx[0]],
+            self.joint_pos[:, self._cart_dof_idx[0]],
+            self.joint_vel[:, self._cart_dof_idx[0]],
+            self.reset_terminated,
+        )
+        return total_reward
+
+    def _get_dones(self) -> tuple[torch.Tensor, torch.Tensor]:
+        self.joint_pos = self.robot.data.joint_pos
+        self.joint_vel = self.robot.data.joint_vel
+
+        time_out = self.episode_length_buf >= self.max_episode_length - 1
+        out_of_bounds = torch.any(torch.abs(self.joint_pos[:, self._cart_dof_idx]) > self.cfg.max_cart_pos, dim=1)
+        out_of_bounds = out_of_bounds | torch.any(torch.abs(self.joint_pos[:, self._pole_dof_idx]) > math.pi / 2, dim=1)
+        return out_of_bounds, time_out
+
+    def _reset_idx(self, env_ids: Sequence[int] | None):
+        if env_ids is None:
+            env_ids = self.robot._ALL_INDICES
+        super()._reset_idx(env_ids)
+
+        joint_pos = self.robot.data.default_joint_pos[env_ids]
+        joint_pos[:, self._pole_dof_idx] += sample_uniform(
+            self.cfg.initial_pole_angle_range[0] * math.pi,
+            self.cfg.initial_pole_angle_range[1] * math.pi,
+            joint_pos[:, self._pole_dof_idx].shape,
+            joint_pos.device,
+        )
+        joint_vel = self.robot.data.default_joint_vel[env_ids]
+
+        default_root_state = self.robot.data.default_root_state[env_ids]
+        default_root_state[:, :3] += self.scene.env_origins[env_ids]
+
+        self.joint_pos[env_ids] = joint_pos
+        self.joint_vel[env_ids] = joint_vel
+
+        self.robot.write_root_pose_to_sim(default_root_state[:, :7], env_ids)
+        self.robot.write_root_velocity_to_sim(default_root_state[:, 7:], env_ids)
+        self.robot.write_joint_state_to_sim(joint_pos, joint_vel, None, env_ids)
+
+
+@torch.jit.script
+def compute_rewards(
+    rew_scale_alive: float,
+    rew_scale_terminated: float,
+    rew_scale_pole_pos: float,
+    rew_scale_cart_vel: float,
+    rew_scale_pole_vel: float,
+    pole_pos: torch.Tensor,
+    pole_vel: torch.Tensor,
+    cart_pos: torch.Tensor,
+    cart_vel: torch.Tensor,
+    reset_terminated: torch.Tensor,
+):
+    rew_alive = rew_scale_alive * (1.0 - reset_terminated.float())
+    rew_termination = rew_scale_terminated * reset_terminated.float()
+    rew_pole_pos = rew_scale_pole_pos * torch.sum(torch.square(pole_pos).unsqueeze(dim=1), dim=-1)
+    rew_cart_vel = rew_scale_cart_vel * torch.sum(torch.abs(cart_vel).unsqueeze(dim=1), dim=-1)
+    rew_pole_vel = rew_scale_pole_vel * torch.sum(torch.abs(pole_vel).unsqueeze(dim=1), dim=-1)
+    total_reward = rew_alive + rew_termination + rew_pole_pos + rew_cart_vel + rew_pole_vel
+    return total_reward
--- a/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/flexr_v0_env_cfg.py
+++ b/source/FLEXR_v0/FLEXR_v0/tasks/direct/flexr_v0/flexr_v0_env_cfg.py
@@ -0,0 +1,48 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+from isaaclab_assets.robots.cartpole import CARTPOLE_CFG
+
+from isaaclab.assets import ArticulationCfg
+from isaaclab.envs import DirectRLEnvCfg
+from isaaclab.scene import InteractiveSceneCfg
+from isaaclab.sim import SimulationCfg
+from isaaclab.utils import configclass
+
+
+@configclass
+class FlexrV0EnvCfg(DirectRLEnvCfg):
+    # env
+    decimation = 2
+    episode_length_s = 5.0
+    # - spaces definition
+    action_space = 1
+    observation_space = 4
+    state_space = 0
+
+    # simulation
+    sim: SimulationCfg = SimulationCfg(dt=1 / 120, render_interval=decimation)
+
+    # robot(s)
+    robot_cfg: ArticulationCfg = CARTPOLE_CFG.replace(prim_path="/World/envs/env_.*/Robot")
+
+    # scene
+    scene: InteractiveSceneCfg = InteractiveSceneCfg(num_envs=4096, env_spacing=4.0, replicate_physics=True)
+
+    # custom parameters/scales
+    # - controllable joint
+    cart_dof_name = "slider_to_cart"
+    pole_dof_name = "cart_to_pole"
+    # - action scale
+    action_scale = 100.0  # [N]
+    # - reward scales
+    rew_scale_alive = 1.0
+    rew_scale_terminated = -2.0
+    rew_scale_pole_pos = -1.0
+    rew_scale_cart_vel = -0.01
+    rew_scale_pole_vel = -0.005
+    # - reset states/conditions
+    initial_pole_angle_range = [-0.25, 0.25]  # pole angle sample range on reset [rad]
+    max_cart_pos = 3.0  # reset if cart exceeds this position [m]
--- a/source/FLEXR_v0/FLEXR_v0/ui_extension_example.py
+++ b/source/FLEXR_v0/FLEXR_v0/ui_extension_example.py
@@ -0,0 +1,46 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+import omni.ext
+
+
+# Functions and vars are available to other extension as usual in python: `example.python_ext.some_public_function(x)`
+def some_public_function(x: int):
+    print("[FLEXR_v0] some_public_function was called with x: ", x)
+    return x**x
+
+
+# Any class derived from `omni.ext.IExt` in top level module (defined in `python.modules` of `extension.toml`) will be
+# instantiated when extension gets enabled and `on_startup(ext_id)` will be called. Later when extension gets disabled
+# on_shutdown() is called.
+class ExampleExtension(omni.ext.IExt):
+    # ext_id is current extension id. It can be used with extension manager to query additional information, like where
+    # this extension is located on filesystem.
+    def on_startup(self, ext_id):
+        print("[FLEXR_v0] startup")
+
+        self._count = 0
+
+        self._window = omni.ui.Window("My Window", width=300, height=300)
+        with self._window.frame:
+            with omni.ui.VStack():
+                label = omni.ui.Label("")
+
+                def on_click():
+                    self._count += 1
+                    label.text = f"count: {self._count}"
+
+                def on_reset():
+                    self._count = 0
+                    label.text = "empty"
+
+                on_reset()
+
+                with omni.ui.HStack():
+                    omni.ui.Button("Add", clicked_fn=on_click)
+                    omni.ui.Button("Reset", clicked_fn=on_reset)
+
+    def on_shutdown(self):
+        print("[FLEXR_v0] shutdown")
--- a/source/FLEXR_v0/config/extension.toml
+++ b/source/FLEXR_v0/config/extension.toml
@@ -0,0 +1,35 @@
+[package]
+
+# Semantic Versioning is used: https://semver.org/
+version = "0.1.0"
+
+# Description
+category = "isaaclab"
+readme  = "README.md"
+
+title = "Extension Template"
+author = "Isaac Lab Project Developers"
+maintainer = "Isaac Lab Project Developers"
+description="Extension Template for Isaac Lab"
+repository = "https://github.com/isaac-sim/IsaacLab.git"
+keywords = ["extension", "template", "isaaclab"]
+
+[dependencies]
+"isaaclab" = {}
+"isaaclab_assets" = {}
+"isaaclab_mimic" = {}
+"isaaclab_rl" = {}
+"isaaclab_tasks" = {}
+# NOTE: Add additional dependencies here
+
+[[python.module]]
+name = "FLEXR_v0"
+
+[isaaclab_settings]
+# TODO: Uncomment and list any apt dependencies here.
+#       If none, leave it commented out.
+# apt_deps = ["example_package"]
+# TODO: Uncomment and provide path to a ros_ws
+#       with rosdeps to be installed. If none,
+#       leave it commented out.
+# ros_ws = "path/from/extension_root/to/ros_ws"
--- a/source/FLEXR_v0/docs/CHANGELOG.rst
+++ b/source/FLEXR_v0/docs/CHANGELOG.rst
@@ -0,0 +1,10 @@
+Changelog
+---------
+
+0.1.0 (2025-06-14)
+~~~~~~~~~~~~~~~~~~
+
+Added
+^^^^^
+
+* Created an initial template for building an extension or project based on Isaac Lab
--- a/source/FLEXR_v0/pyproject.toml
+++ b/source/FLEXR_v0/pyproject.toml
@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools", "wheel", "toml"]
+build-backend = "setuptools.build_meta"
--- a/source/FLEXR_v0/setup.py
+++ b/source/FLEXR_v0/setup.py
@@ -0,0 +1,44 @@
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Installation script for the 'FLEXR_v0' python package."""
+
+import os
+import toml
+
+from setuptools import setup
+
+# Obtain the extension data from the extension.toml file
+EXTENSION_PATH = os.path.dirname(os.path.realpath(__file__))
+# Read the extension.toml file
+EXTENSION_TOML_DATA = toml.load(os.path.join(EXTENSION_PATH, "config", "extension.toml"))
+
+# Minimum dependencies required prior to installation
+INSTALL_REQUIRES = [
+    # NOTE: Add dependencies
+    "psutil",
+]
+
+# Installation operation
+setup(
+    name="FLEXR_v0",
+    packages=["FLEXR_v0"],
+    author=EXTENSION_TOML_DATA["package"]["author"],
+    maintainer=EXTENSION_TOML_DATA["package"]["maintainer"],
+    url=EXTENSION_TOML_DATA["package"]["repository"],
+    version=EXTENSION_TOML_DATA["package"]["version"],
+    description=EXTENSION_TOML_DATA["package"]["description"],
+    keywords=EXTENSION_TOML_DATA["package"]["keywords"],
+    install_requires=INSTALL_REQUIRES,
+    license="MIT",
+    include_package_data=True,
+    python_requires=">=3.10",
+    classifiers=[
+        "Natural Language :: English",
+        "Programming Language :: Python :: 3.10",
+        "Isaac Sim :: 4.5.0",
+    ],
+    zip_safe=False,
+)