brax 开源项目推荐（37 个）

EMI-Group /tensorneat

GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)

Simple-Robotics /Simple

The Simple Simulator: Simulation Made Simple

EMI-Group /metade

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.

JacopoPan /a-minimalist-guide

Walkthroughs for DSL, AirSim, the Vector Institute, and more

perrin-isir /xpag

a modular reinforcement learning library with JAX agents

Andrew-Luo1 /jax_shac

An implementation of Short Horizon Actor Critic writen in Jax. Core algorithm written in the style of Brax, with several bits taken from Xu's original paper.

EMI-Group /tensorrvea

GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA.

pal-robotics /brax_training_viewer

Brax Viewer is a real-time, interactive web viewer for monitoring reinforcement learning (RL) policies

rystrauss /dopamax

纯JAX中的强化学习。

mohammadzainabbas /Reinforcement-Learning-CS

💡 Grasp - Pick-and-place with a robotic hand 👨🏻‍💻

giorgia-nadizar /cgpax

Simple implementations of Cartesian Genetic Programming (CGP) and Linear Genetic Programming (LGP) in JAX

tartavull /alfredo

Relentlessly learning, persistently failing, but never surrendering.

alpc91 /SMERL

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

TC635807 /mjx-go2-training

Unitree Go2 terrain locomotion trained with MJX / MuJoCo Warp + Brax PPO on a single 8 GB GPU - 20.97M steps, 1536-768 MLP, stairs 0.03-0.05 m

kevinxqiu /debate2create

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

weiwei-gu /Orthrus

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

BRAXapp /apa7-docs

APA-7 powered academic document editor online. Branded as "Acado".

YauhenBichel /humanoid-companion

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.

tomalner18 /MAax

用于加速多智能体强化学习的程序化环境生成

mohamedarifq8-alt /Unitree-G1-RL

Training a Unitree G1 Humanoid Robot to walk using PPO, JAX, and Brax. Achieved via End-to-End GPU Simulation (4096 parallel environments) and 200M timesteps of Curriculum Learning.