isaac-sim/OmniIsaacGymEnvs

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

1048 stars · 236 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of GPU-accelerated reinforcement learning environments built on NVIDIA Isaac Sim and the omni.isaac.gym framework, with PPO training examples via rl_games. It is now in maintenance mode, with development merged into IsaacLab.

Use cases

• train RL policies for robotics in simulation
• run GPU-parallel reinforcement learning environments
• learn robot locomotion and manipulation with PPO
• simulate physics-based RL tasks in Isaac Sim
• benchmark RL algorithms on robotics tasks

When to choose

• you need RL environments running on Isaac Sim's physics and rendering stack
• you want ready-made PPO examples for robotics tasks
• you are maintaining existing projects built on OmniIsaacGymEnvs

When to avoid

• you are starting a new project - use IsaacLab instead, which absorbed this repo
• you do not have a GPU with at least 12GB VRAM and Isaac Sim installed
• you need non-robotics or lightweight RL environments

Facets

library · maturity maintenance

reinforcement-learning simulation machine-learning reinforcement-learning robotics simulation machine-learning python windows isaac-sim omniverse rl-games ppo gpu-simulation robot-learning deprecated-in-favor-of-isaac-lab gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="isaac-sim/OmniIsaacGymEnvs")