nicrusso7/rex-gym

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1102 stars · 140 forks observed · 2026-08-28

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

Rex-gym provides OpenAI Gym environments for the open-source SpotMicro quadruped robot, built on PyBullet simulation, along with a PPO learning agent and training scripts. It includes a CLI for batch training, rendering single training sessions, and replaying learned control policies intended for sim-to-real transfer to the physical robot.

Use cases

• train a quadruped robot with reinforcement learning in simulation
• create custom OpenAI Gym environments for legged robots
• run PPO training on a PyBullet robot simulation
• transfer learned control policies from simulation to a real SpotMicro robot
• visualize pre-trained quadruped gaits and policies
• experiment with inverse kinematics vs open-loop gait controllers

When to choose

• you want to learn or teach reinforcement learning on a realistic legged-robot simulation
• you own or plan to build a SpotMicro quadruped and want sim-to-real policies
• you need ready-made Gym environments with PyBullet for quadruped locomotion research

When to avoid

• you need a maintained, actively updated project (last release 2023, Python 3.7 era)
• you work with robots other than SpotMicro-style quadrupeds
• you need modern RL frameworks or GPU-accelerated simulation rather than TensorFlow/PyBullet

Facets

library · maturity maintenance

reinforcement-learning simulation machine-learning cli robotics reinforcement-learning artificial-intelligence simulation python windows openai-gym pybullet quadruped-robot spotmicro ppo inverse-kinematics sim-to-real legged-robots linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nicrusso7/rex-gym")