#reinforcement-learning

RL environments + evals for AI agents. Define once, train anything.

MQT Predictor - A Tool for Automatic Device Selection with Device-Specific Circuit Compilation for Quantum Computing

Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

A Python SDK and CLI for building agent rollouts and managing LLM post-training workflows on Osmosis.

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

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

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

MuJoco Simulation on WebAssembly with Neural networks

MuJoCo bindings and high-level wrappers for the Rust programming language. Includes the viewer.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Gym environment for building simulation and control using reinforcement learning

Fast and differentiable particle accelerator optics simulation for reinforcement learning and optimisation applications.