Multi-Joint dynamics with Contact. A general purpose physics simulator.

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

An open-source unsupervised RL framework for humanoid control with FB/TeCH training, robot-aware motion import, and real-world teleoperation.

Official code release for Play2Perfect: a 2-stage RL pipeline for contact-rich assembly (arXiv 2606.26428)

An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

Judo: a hackable sampling-based MPC toolbox

Let's move Flexiv! Simulation and Control at 1 KHz with Python + Cyclone DDS + CPP Driver.

A benchmark for offline goal-conditioned RL and offline RL

Evolution Strategies in JAX 🦎

Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.

The official implementation of flow Q-learning (FQL)

A Python interface and simulation environemtn for the Unitree Go2 robot.

Sampling-based model predictive control on GPU with JAX/MJX

Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing". DIAL-MPC is a novel sampling-based MPC framework for legged …

RL Environments in JAX 🌍

Accelerated Quality-Diversity

EvoRL is a fully GPU-accelerated framework for Evolutionary Reinforcement Learning, implemented with JAX. It supports Reinforcement Learning (RL), Evolutionary Computation (EC), Evolution-guided Re…

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Program synthesis by RL

An easy-to-use reinforcement learning library for research and education.

The Advanced Proximal Optimization Toolbox