isaac-sim/IsaacGymEnvs

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

2952 stars · 513 forks observed · 2026-08-28

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

A collection of example reinforcement learning environments for NVIDIA Isaac Gym, a GPU-accelerated physics simulator. It provides a Gym-style API for creating thousands of vectorized parallel environments and benchmark tasks like Cartpole and Ant locomotion.

Use cases

• train RL policies on GPU-accelerated physics simulation
• benchmark reinforcement learning algorithms on standard tasks
• run thousands of parallel physics environments for RL training
• learn robot locomotion like Ant walking
• prototype RL environments with a Gym-compatible API

When to choose

• you need massively parallel RL environment simulation on NVIDIA GPUs
• you want ready-made benchmark tasks from the Isaac Gym NeurIPS paper
• you already have Isaac Gym Preview 4 installed and want example environments

When to avoid

• you don't have an NVIDIA GPU or Isaac Gym Preview 4 access
• you need the newer Isaac Lab / Isaac Sim ecosystem instead
• you need CPU-only or non-NVIDIA simulation

Facets

library · maturity maintenance

reinforcement-learning simulation benchmarking machine-learning reinforcement-learning robotics simulation machine-learning gpu-computing python isaac-gym nvidia physics-simulation gym-environments rl-training robot-locomotion vectorized-environments linux gpu docker

Member repositories

For agents

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