Skip to content
Back to search

IsaacLab-Arena

Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot learning policies. The framework enables developers to rapidly prototype and test robotic tasks with various robot embodiments, objects, and environments.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/isaac-sim/IsaacLab-Arena with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/isaac-sim/IsaacLab-Arena'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/isaac-sim--isaaclab-arena/badge.svg)](/listings/isaac-sim--isaaclab-arena)

HTML

<a href="/listings/isaac-sim--isaaclab-arena"><img src="/api/listings/isaac-sim--isaaclab-arena/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

- Linux (Ubuntu 22.04+) - NVIDIA GPU (see [Isaac Sim hardware requirements](https://docs.isaacsim.omniverse.nvidia.com/6.0.0/installation/requirements.html)) - [uv](https://docs.astral.sh/uv/) (for the native install), or Docker and the NVIDIA Container Toolkit (for the container install) - Git

Installation

**Native developer setup with uv:**

# 1. Clone the repository
git clone --recurse-submodules git@github.com:isaac-sim/IsaacLab-Arena.git
cd IsaacLab-Arena

# 2. Create the locked environment (Isaac Lab from source, plus the Isaac Sim, PyTorch, and Newton wheels)
uv sync

# 3. Activate the environment and accept the Isaac Sim EULA
source .venv/bin/activate
export OMNI_KIT_ACCEPT_EULA=YES ACCEPT_EULA=Y

# 4. Verify the installation with a short zero-action rollout
python isaaclab_arena/evaluation/policy_runner.py \
  --policy_type zero_action --num_steps 20 cube_goal_pose

# 4b. (Optional) Watch the rollout in the GUI visualizer
python isaaclab_arena/evaluation/policy_runner.py \
  --viz kit --policy_type zero_action --num_steps 200 cube_goal_pose

> **Note:** See our > [installation docs](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.0/pages/quickstart/installation.html) > for more details and installation flavors.

**Source install inside Docker:**

# 1. Clone the repository
git clone git@github.com:isaac-sim/IsaacLab-Arena.git
cd IsaacLab-Arena
git submodule update --init --recursive

# 2. Launch the Docker container
#    Base container (recommended for development):
./docker/run_docker.sh

#    Or with GR00T dependencies (for policy training/evaluation):
./docker/run_docker.sh -g

# 3. Verify the installation with a short zero-action rollout
/isaac-sim/python.sh isaaclab_arena/evaluation/policy_runner.py \
  --policy_type zero_action --num_steps 20 cube_goal_pose

# 3b. (Optional) Watch the rollout in the GUI visualizer
/isaac-sim/python.sh isaaclab_arena/evaluation/policy_runner.py \
  --viz kit --policy_type zero_action --num_steps 200 cube_goal_pose

> **Note:** The Docker script automatically mounts `$HOME/datasets`, `$HOME/models`, and `$HOME/eval` from your host into the container.

For detailed setup instructions (including server-client mode for GR00T), see the [Installation Guide](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.0/pages/quickstart/installation.html).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 336 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. # Isaac Lab-Arena
  3. ### Composable Environment Creation and Policy Evaluation for Robotics Simulation
  4. [![Alpha](https://img.shields.io/badge/status-alpha-e8912d.svg)](#%EF%B8%8F-project-status)
  5. [![Version](https://img.shields.io/badge/version-0.3-blue.svg)](https://github.com/isaac-sim/IsaacLab-Arena/tree/main)
  6. [![IsaacSim](https://img.shields.io/badge/IsaacSim-6.2.0-silver.svg)](https://docs.isaacsim.omniverse.nvidia.com/latest/index.html)
  7. [![IsaacLab](https://img.shields.io/badge/IsaacLab-3.0.0-silver.svg)](https://github.com/isaac-sim/IsaacLab)
  8. [![Python](https://img.shields.io/badge/python-≥3.12-blue.svg)](https://docs.python.org/3/whatsnew/3.12.html)
  9. [![Linux](https://img.shields.io/badge/platform-linux--64-orange.svg)](https://releases.ubuntu.com/22.04/)
  10. [![License](https://img.shields.io/badge/license-Apache--2.0-yellow.svg)](LICENSE.md)
  11. [Documentation](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/index.html) · [NVIDIA Blog Post](https://developer.nvidia.com/blog/simplify-generalist-robot-policy-evaluation-in-simulation-with-nvidia-isaac-lab-arena/) · [Report a Bug](https://github.com/isaac-sim/IsaacLab-Arena/issues) · [Discussions](https://github.com/isaac-sim/IsaacLab-Arena/discussions)
  12. </div>
  13. ---
  14. > [!WARNING]
  15. > **Alpha Software — Not an Early Access or General Availability Release.**
  16. > Isaac Lab-Arena `v0.3` is an early code release intended to give the community a practical starting point to experiment, provide feedback, and influence future design direction. APIs are unstable and will change. Features are incomplete. Documentation is evolving. **Do not use this in production.** See [Project Status](#%EF%B8%8F-project-status) for details.
  17. > [!NOTE]
  18. > Changes on `main` contain an in-development version based on v0.3.1 and Isaac Lab 3.0.
  19. ---
  20. ## Overview
  21. **Isaac Lab-Arena** is an open-source framework for scalable benchmark authoring and robot policy evaluation in simulation. It extends [NVIDIA Isaac Lab](https://github.com/isaac-sim/IsaacLab) with reusable APIs to author benchmarks, execute evaluations at scale, and analyze results for actionable feedback.
  22. Instead of hand-writing and maintaining a separate configuration for every combination of robot,
  23. object, and scenario, Arena composes environments from three independent primitives: a **scene**,
  24. which defines the physical layout and its objects, furniture, and fixtures; an **embodiment**, which
  25. defines the robot, observations, actions, sensors, and controllers; and a **task**, which defines what
  26. the robot must accomplish. `ArenaEnvBuilder` combines them into a standard `ManagerBasedRLEnvCfg`
  27. that runs natively in Isaac Lab.
  28. Building on that foundation, Arena provides three connected capabilities across the benchmark and policy-evaluation workflow:
  29. | Workflow | What Arena provides |
  30. |----------|---------------------|
  31. | **Author** | Build reusable benchmark environments through modular composition, relational placement, agentic authoring, and controlled variations. Register Arena environments with Isaac Lab for learning and data generation. |
  32. | **Execute** | Evaluate one policy concurrently across thousands of heterogeneous environments on a GPU. Package multiple tasks and policies as experiments that run locally or across nodes through OSMO and a common policy client. |
  33. | **Analyze** | Collect aggregate and per-episode metrics, trace predicate-based subtask progress, and run sensitivity analysis over controlled conditions to see where and why policies fail. |
  34. ## Why Isaac Lab-Arena?
  35. See the [documentation overview](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/index.html#why-isaac-lab-arena) for the motivation behind Arena and how it addresses evaluation scale, reproducibility, and failure diagnosis.
  36. ## Key Features
  37. ### Author Scalable Benchmarks
  38. - **Composable environments** — Configure scenes, embodiments, and tasks independently, with reusable objects composed into each scene. `ArenaEnvBuilder` assembles them into an Isaac Lab environment without duplicating task logic.
  39. - **Relational object placement** — Define layouts with spatial relationships such as "on" and "next to" instead of hard-coded coordinates.
  40. - **Sequential task chaining** — Chain atomic skills (pick, walk, place, …) into long-horizon composite tasks.
  41. - **Agentic authoring** — Use coding agents with Arena's authoring skill, placement relations, and composite tasks to build and validate evaluation environments.
  42. - **Controlled environment variations** — Turn one environment into a perturbation sweep over lighting, backgrounds, camera parameters, object mass, and other configurable ranges and distributions.
  43. - **Isaac Lab interoperability** — Register Arena-authored environments with Isaac Lab workflows for reinforcement learning and data generation.
  44. - **Newton-backed deformable and contact-rich simulation** — Build evaluation environments for deformable-object manipulation and contact-rich assembly, such as gear insertion, using the Newton physics backend and Arena's evaluation tools.
  45. ### Execute Evaluations at Scale
  46. - **GPU-accelerated parallel evaluation** — Evaluate one policy across thousands of heterogeneous environments concurrently instead of running sequential rollouts.
  47. - **Large-scale multi-node evaluation** — Define experiments with multiple tasks and policies, run locally or distribute them with an orchestrator such as OSMO, and collect aggregate metrics plus per-episode results.
  48. - **Policy client-server architecture** — Evaluate GR00T, π0.5, VLMs, or a custom policy behind a server through a common observation-and-action contract.
  49. - **Streamlined setup and agent skills** — Use the native `uv` installation path and reusable agent skills for key workflows.
  50. ### Analyze Policy Robustness
  51. - **Subtask predicates** — Track milestones such as grasp, lift, transport, and place to pinpoint where a policy fails.
  52. - **Sensitivity analysis** — Perturb environment factors to reveal robustness gaps and generate actionable feedback for targeted policy learning.
  53. ## Quick Start
  54. ### Prerequisites
  55. - Linux (Ubuntu 22.04+)
  56. - NVIDIA GPU (see [Isaac Sim hardware requirements](https://docs.isaacsim.omniverse.nvidia.com/6.2.0/installation/requirements.html))
  57. - NVIDIA driver 580 or newer (Arena uses PyTorch built for CUDA 13.0)
  58. - [uv](https://docs.astral.sh/uv/) (for the native install), or Docker and the NVIDIA Container Toolkit (for the container install)
  59. - Git
  60. ### Installation
  61. **Native developer setup with uv:**
  62. ```bash
  63. # 1. Clone the repository
  64. git clone --recurse-submodules git@github.com:isaac-sim/IsaacLab-Arena.git
  65. cd IsaacLab-Arena
  66. # 2. Create the locked environment (Isaac Lab from source, plus the Isaac Sim, PyTorch, and Newton wheels)
  67. uv sync
  68. # 3. Activate the environment and accept the Isaac Sim EULA
  69. source .venv/bin/activate
  70. export OMNI_KIT_ACCEPT_EULA=YES ACCEPT_EULA=Y
  71. # 4. Verify the installation with a short zero-action rollout
  72. python isaaclab_arena/evaluation/experiment_runner.py
  73. # 4b. (Optional) Watch the rollout in the GUI visualizer
  74. python isaaclab_arena/evaluation/experiment_runner.py \
  75. --viz kit runs.smoke_test.rollout_limit.num_steps=200
  76. ```
  77. > **Note:** See our
  78. > [installation docs](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/quickstart/installation.html)
  79. > for more details and installation flavors.
  80. **Source install inside Docker:**
  81. ```bash
  82. # 1. Clone the repository
  83. git clone git@github.com:isaac-sim/IsaacLab-Arena.git
  84. cd IsaacLab-Arena
  85. git submodule update --init --recursive
  86. # 2. Launch the Docker container
  87. # Base container (recommended for development):
  88. ./docker/run_docker.sh
  89. # Or with GR00T dependencies (for policy training/evaluation):
  90. ./docker/run_docker.sh -g
  91. # 3. Verify the installation with a short zero-action rollout
  92. python isaaclab_arena/evaluation/experiment_runner.py
  93. # 3b. (Optional) Watch the rollout in the GUI visualizer
  94. python isaaclab_arena/evaluation/experiment_runner.py \
  95. --viz kit runs.smoke_test.rollout_limit.num_steps=200
  96. ```
  97. > **Note:** The Docker script automatically mounts `$HOME/datasets`, `$HOME/models`, and `$HOME/eval` from your host into the container.
  98. For detailed setup instructions (including server-client mode for GR00T), see the [Installation Guide](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/quickstart/installation.html).
  99. ## Usage Example
  100. Compose a Franka arm in a kitchen scene with a couple of objects:
  101. ```python
  102. from isaaclab_arena.assets.asset_registry import AssetRegistry
  103. from isaaclab_arena.environments.arena_env_builder import ArenaEnvBuilder, ArenaEnvBuilderCfg
  104. from isaaclab_arena.environments.isaaclab_arena_environment import IsaacLabArenaEnvironment
  105. from isaaclab_arena.scene.scene import Scene
  106. asset_registry = AssetRegistry()
  107. # Select building blocks
  108. background = asset_registry.get_asset_by_name("kitchen")()
  109. embodiment = asset_registry.get_asset_by_name("franka_ik")()
  110. cracker_box = asset_registry.get_asset_by_name("cracker_box")()
  111. tomato_soup_can = asset_registry.get_asset_by_name("tomato_soup_can")()
  112. # Compose the environment
  113. scene = Scene(assets=[background, cracker_box, tomato_soup_can])
  114. env_cfg = IsaacLabArenaEnvironment(
  115. name="franka_kitchen_example",
  116. embodiment=embodiment,
  117. scene=scene,
  118. )
  119. builder_cfg = ArenaEnvBuilderCfg()
  120. env_builder = ArenaEnvBuilder(env_cfg, builder_cfg)
  121. env = env_builder.make_registered()
  122. env.reset()
  123. ```
  124. Python callers set builder options directly on `ArenaEnvBuilderCfg`. Runner scripts
  125. continue to accept the same options as CLI flags, such as `--num_envs 4 --seed 7`,
  126. and translate them into an `ArenaEnvBuilderCfg` before building the environment.
  127. ### Continue in the Documentation
  128. #### Getting Started
  129. Choose a guide based on what you want to do:
  130. - [First Arena Environment](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/quickstart/arena_env.html) — Compose a scene, embodiment, and task into a reusable environment.
  131. - [First Arena Experiment](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/quickstart/arena_experiment.html) — Define and run multiple evaluation configurations as one experiment.
  132. - [Exploring Environment Variations](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/quickstart/environment_variations.html) — Sample controlled changes to lighting, cameras, and backgrounds.
  133. - [Running a Real Policy](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/quickstart/running_a_real_policy/index.html) — Evaluate a pretrained policy from a saved configuration.
  134. #### Ready-to-Use Environments
  135. - [Example Environments](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/example_workflows/example_environments.html) — Browse Python-registered environments, RoboLab-inspired tasks, and Kitchen Benchmark specifications.
  136. #### Example Workflows
  137. Explore complete workflows for:
  138. - [Evaluation](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/example_workflows/analysis/index.html) — Run controlled sweeps and analyze the conditions associated with policy success or failure.
  139. - [Imitation Learning](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/example_workflows/imitation_learning/index.html) — Collect data, post-train a policy, and run closed-loop evaluation.
  140. - [Reinforcement Learning](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/example_workflows/reinforcement_learning_workflows/index.html) — Set up an environment, train a policy, and run closed-loop evaluation.
  141. ## Project Structure
  142. ```
  143. IsaacLab-Arena/
  144. ├── isaaclab_arena/ # Core framework (environments, tasks, scenes, embodiments)
  145. ├── isaaclab_arena_environments/ # Concrete environment definitions
  146. ├── isaaclab_arena_examples/ # Policy and relation examples
  147. ├── isaaclab_arena_g1/ # Unitree G1 humanoid embodiment + examples
  148. ├── isaaclab_arena_dreamzero/ # DreamZero policy integration
  149. ├── isaaclab_arena_gr00t/ # GR00T policy integration
  150. ├── isaaclab_arena_openpi/ # OpenPi (pi0 / pi05) policy integration
  151. ├── docker/ # Docker configurations and launch scripts
  152. ├── docs/ # Sphinx documentation source
  153. ├── osmo/ # Cloud deployment configs (OSMO)
  154. ├── submodules/ # Git submodules (Isaac Lab, etc.)
  155. ├── pyproject.toml # Package metadata, dependencies, and uv config
  156. ├── CONTRIBUTING.md # Contribution guidelines
  157. └── LICENSE.md # Apache 2.0 license
  158. ```
  159. ## Version Compatibility
  160. | Isaac Lab-Arena | Isaac Lab | Isaac Sim | Python |
  161. | ------------------------------- | ----------- | --------- | ------ |
  162. | `main` | 3.0.0 | 6.2.0 | ≥ 3.12 |
  163. | `release/0.3.1` | 3.0.0 EA | 6.1.0 | ≥ 3.12 |
  164. | `release/0.3.0` | 3.0.0 beta2 | 6.0.1 | ≥ 3.12 |
  165. | `release/0.2.1` | 3.0.0 beta | 6.0.0 | ≥ 3.12 |
  166. | `release/0.2.0` | 3.0.0 beta | 6.0.0 | ≥ 3.12 |
  167. | `feature/arena_v0.2_on_lab_2.3` | 2.3.0 | 5.1.0 | ≥ 3.10 |
  168. | `release/0.1.1` | 2.3.0 | 5.0.0 | ≥ 3.10 |
  169. | `release/0.1.0` | 2.3.0 | 5.0.0 | ≥ 3.10 |
  170. ## ⚠️ Project Status
  171. Isaac Lab-Arena is in **alpha** (`v0.3`). This is important to understand:
  172. | What This Means | Details |
  173. |-----------------|---------|
  174. | **Not EA / GA** | This is not an Early Access or General Availability release. It is a very early community code drop. |
  175. | **APIs will break** | Public interfaces are under active development and will change without deprecation warnings. |
  176. | **Features are evolving** | Performance is not yet hardened for production-scale workloads, and benchmark and analysis coverage continues to expand. |
  177. | **Limited testing** | The `main` branch contains the latest code but may not be fully tested. Use `release/0.3.1` for the most stable experience. |
  178. ## Ecosystem
  179. Isaac Lab-Arena is part of a growing ecosystem of tools and benchmarks. NVIDIA is working with benchmark authors and model developers to build, run, and open-source benchmarks on Arena.
  180. The ecosystem extends beyond pick-and-place to contact-rich, dexterous, and deformable benchmarks for industry and academia. Arena's modular foundation lets you reuse them as low-cost readiness gates or adapt their building blocks—tasks, scenes, robots, and evaluation methods—for custom evaluations.
  181. ### Published Benchmarks
  182. - **[Lightwheel RoboFinals](https://lightwheel.ai/robofinals)** — High-fidelity industrial benchmarks.
  183. - **[Lightwheel RoboCasa Tasks](https://github.com/LightwheelAI/LW-BenchHub)** — 138+ open-source tasks, 50 datasets per task, 7+ robots.
  184. - **[Lightwheel LIBERO Tasks](https://github.com/LightwheelAI/LW-BenchHub)** — Adapted LIBERO benchmarks.
  185. - [**RoboTwin 2.0**](https://github.com/RoboTwin-Platform/RoboTwin/tree/IsaacLab-Arena) — Extended simulation benchmarks using Arena; [arXiv](https://arxiv.org/abs/2603.01229).
  186. - **[LeRobot Environment Hub](https://huggingface.co/blog/nvidia/generalist-robotpolicy-eval-isaaclab-arena-lerobot)** — Share and discover Arena environments on Hugging Face.
  187. - **[Isaac for Healthcare RHEO Workflows](https://github.com/isaac-for-healthcare/i4h-workflows/tree/main/workflows/rheo)** — Healthcare robotics benchmark workflows.
  188. - **[RoboDojo](https://github.com/RoboDojo-Benchmark/RoboDojo/tree/RoboDojo-IsaacLabArena)** — A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies.
  189. - **[VABAR](https://berkeleyautomation.github.io/vabar-website/)** — A benchmark for robots that repeat one job across a known distribution of variation.
  190. - **[DexBench](https://dexbench.ai)** — Measuring dexterity where it matters.
  191. - **[X2Real](https://github.com/X-Square-Robot/x2real)** — An eXtensive simulation benchmark for real-world generalist policies.
  192. ### Coming Soon
  193. Coming soon: support for the full RoboTwin task suite, plus benchmark integrations
  194. from ecosystem partners including Sharpa and NVIDIA
  195. GEAR (G1 Factory), with more partner benchmarks to follow.
  196. ### Publishing Your Own Benchmark
  197. We encourage the community to build and publish benchmarks on Isaac Lab-Arena. The recommended workflow:
  198. 1. **Maintain your benchmark in your own repository.** Create a branch or package that integrates with Isaac Lab-Arena (e.g. an `IsaacLab-Arena` branch). For detailed setup instructions—including repository layout, Dockerfile setup, and how to register custom environments, robots, and tasks—see the [Arena in Your Repository](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/pages/arena_in_your_repo/index.html) guide.
  199. 2. **Reference your benchmark and Isaac Lab-Arena in publications.** When publishing on ArXiv or elsewhere, cite both your benchmark (by name, with a link to your repository) and Isaac Lab-Arena as the underlying evaluation framework.
  200. 3. **List it here.** Open a PR to add your benchmark to the [Published Benchmarks](#published-benchmarks) list above. This README serves as the single source of truth for the Arena benchmark ecosystem so the community can discover and reuse.
  201. ## Contributing
  202. We welcome contributions — bug reports, feature suggestions, and code. This is an alpha project, so community input directly shapes the framework's direction.
  203. 1. Read the [Contribution Guidelines](CONTRIBUTING.md)
  204. 2. For new features, public API changes, or significant design changes, open a [Design Proposal](https://github.com/isaac-sim/IsaacLab-Arena/issues/new?template=design-proposal.yml) before submitting a full implementation
  205. 3. Sign off your commits (DCO required — see `CONTRIBUTING.md`)
  206. 4. Open a [Pull Request](https://github.com/isaac-sim/IsaacLab-Arena/pulls)
  207. Areas where contributions are especially valuable:
  208. - New task definitions and benchmark suites
  209. - Additional robot embodiments and scene assets
  210. - Sim-to-real validated evaluation methods
  211. - Documentation improvements and tutorials
  212. ## Support
  213. - **Questions & Ideas** — [GitHub Discussions](https://github.com/isaac-sim/IsaacLab-Arena/discussions)
  214. - **Bug Reports** — [GitHub Issues](https://github.com/isaac-sim/IsaacLab-Arena/issues)
  215. - **Isaac Sim Questions** — [NVIDIA Forums](https://forums.developer.nvidia.com/c/agx-autonomous-machines/isaac/67)
  216. - **Community Chat** — [Omniverse Discord](https://discord.com/invite/nvidiaomniverse)
  217. ## License
  218. Isaac Lab-Arena is released under the [Apache 2.0 License](LICENSE.md).
  219. Note that Isaac Lab-Arena requires Isaac Sim, which includes components under proprietary licensing terms. See the [Isaac Sim license](https://docs.isaacsim.omniverse.nvidia.com/latest/common/NVIDIA_Omniverse_License_Agreement.html) for details.
  220. ## Citation
  221. If you use Isaac Lab-Arena in your research, please cite:
  222. ```bibtex
  223. @misc{isaaclab-arena2025,
  224. title = {Isaac Lab-Arena: Composable Environment Creation and Policy Evaluation for Robotics},
  225. author = {{NVIDIA Isaac Lab-Arena Contributors}},
  226. year = {2025},
  227. url = {https://github.com/isaac-sim/IsaacLab-Arena}
  228. }
  229. ```
  230. If you use Isaac Lab (the underlying framework), please also cite the [Isaac Lab paper](https://arxiv.org/abs/2511.04831).
  231. ## Acknowledgements
  232. Isaac Lab-Arena builds on [NVIDIA Isaac Lab](https://github.com/isaac-sim/IsaacLab), with the evaluation and task layers designed in close collaboration with Lightwheel. We thank the Isaac Lab team and the broader robotics community for their foundational work.
  233. Isaac Lab-Arena was built in collaboration with the authors of Robolab ([website](https://research.nvidia.com/labs/srl/projects/robolab/), [paper](https://arxiv.org/abs/2604.09860)).
  234. ---
  235. <div align="center">
  236. **Isaac Lab-Arena** · Alpha · [Documentation](https://isaac-sim.github.io/IsaacLab-Arena/release/0.3.1/index.html) · [GitHub](https://github.com/isaac-sim/IsaacLab-Arena)
  237. Made with ❤️ by the NVIDIA Robotics Team
  238. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.