Bimo is an open-source bipedal robotics platform with a Python API, fully 3D printable, and an Isaac Lab environment implementation with working sim-to-real transfer.

Open-source research platform for dinosaur biomechanics and robotic locomotion using reinforcement learning. MuJoCo-based Gymnasium environments with curriculum learning, W&B experiment tracking, a…

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

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Turned based strategy game with the goal of developing reinforcement learning algorithms

An open-source AI agent that brings the power of Gemini directly into your terminal.

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.

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

Reinforcement learning library with support for pcsx2 and opengl, among other cores.

Official Implementation of HIMA (COLM'25)

GPU-based Massively Parallel Environments for Large-Scale Combinatorial Optimization (CO) Problems Using Reinforcement Learning

PotoTwin Reinforcement Learning Examples

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Async RL Training at Scale

🦖 Chrome Dinosaur Game in build with Pygame in Python.

A non-saturating, open-ended environment for evaluating LLMs in Factorio

Mastering Diverse Domains through World Models

Distributed Reinforcement Learning accelerated by Lightning Fabric

Simplest and Cleanest DreamerV3 implementation out there

A generative world for general-purpose robotics & embodied AI learning.

AI Robotics tutorials for hobbyists

The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.

Official implementation for SIGGRAPH 2023 paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"

A fully configured development environment for the Autodrive RoboRacer Sim Racing competition

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code