brax

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)

MetaDE is a GPU-accelerated evolutionary framework that optimizes Differential Evolution (DE) strategies via meta-level evolution. Supporting both JAX and PyTorch, it dynamically adapts mutation and crossover strategies for efficient large-scale black-box optimization.

a modular reinforcement learning library with JAX agents

GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA.

Reinforcement learning in pure JAX.

Relentlessly learning, persistently failing, but never surrendering.

[ICML 2024] Official environments and JAX-implementations for "Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments"

[ICML 2026] Debate2Create: Robot Co-design via Multi-Agent LLM Debate

四足机器人 Go2 全栈控制：Convex MPC · RL（BC/PPO/域随机化）· 混合仲裁，同一套 72 试验推力协议下恢复率 94% —— 全程 CPU 训练，附与代码逐项一致的数学设计文档

Procedural Environment Generation for Accelerated Multi-Agent Reinforcement Learning

A small humanoid robot you can talk to: walks with a reinforcement-learned policy, waves and dances, shows a face with lip sync and speaks - its brain is a local LLM you run yourself (Ollama or any OpenAI-compatible API). MuJoCo simulation, sim-to-real.

PPO solves all 11 Gymnasium MuJoCo tasks (Brax/MJX + SB3)