ppo repositories

Trending repositories tagged ppo, ranked by trending score. Updated daily.

  1. 1
    walkinglabs/hands-on-modern-rl

    🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

    GitHub · Jupyter Notebook · 4,939 stars · 367 forks · +182 stars in 24 hours · Trending score 3.79

  2. 2
    agi-brain/xuance

    XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

    GitHub · Python · 1,113 stars · 162 forks · +25 stars in 24 hours · Trending score 2.22

  3. 3
    Robot-Nav/legbot_lab

    legbot四足/四轮足机器人Isaac lab训练框架,包含PPO、PPO+MoE+CTS、WF-CTS-MOE(四轮足训练:真机已验证多种地形的鲁棒运动),可实现多种地形下的鲁棒运动控制。

    GitHub · Python · 64 stars · 5 forks · +20 stars in 24 hours · Trending score 2.18

  4. 4
    Vottivott/microduck-playground

    Reproducible Microduck RL experiments, policies, simulation assets, and hardware add-ons

    GitHub · Python · 154 stars · 15 forks · +13 stars in 24 hours · Trending score 1.82

  5. 5
    tommy85/MirrorForce

    Yu-Gi-Oh! (YGO) AI trained by self-play reinforcement learning on the YGOPro engine; champion of the first YGO agent competition

    GitHub · Python · 17 stars · 2 forks · +6 stars in 24 hours · Trending score 1.46

  6. 6
    wonseokjung/connect-tycoon

    시뮬레이터로 기업 의사결정 모델을 학습시키는 오픈소스 강화학습 게임 · JEV · PPO · Human-in-the-loop

    GitHub · Python · 12 stars · 20 forks · +5 stars in 24 hours · Trending score 1.46

  7. 7
    Enping-Hu/minimind-deep-dive

    从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

    GitHub · Python · 223 stars · 14 forks · +7 stars in 24 hours · Trending score 1.45

  8. 8
    YuvrajSingh-mist/NeatRL

    Readable single-file PyTorch implementations of deep RL algorithms

    GitHub · Python · 241 stars · 22 forks · +5 stars in 24 hours · Trending score 1.21

  9. 9
    AsterisCrack/BipedRobot

    Biped robot locomotion with deep RL: Isaac Lab + MuJoCo, custom PPO/SAC/DDPG/D4PG/MPO, MLP/LSTM/Transformer, motion imitation, sim-to-real

    GitHub · Python · 25 stars · 5 forks · +4 stars in 24 hours · Trending score 1.06

  10. 10
    RobinKa/warcraftsim

    Headless Warcraft III (Legacy TFT 1.29) under Wine for reinforcement learning: the real game stepped from Python, with PufferLib 5 training, behavior cloning and a training dashboard.

    GitHub · Python · 35 stars · 2 forks · +2 stars in 24 hours · Trending score 1.02

  11. 11
    Robot-Nav/GO2_backflip

    宇树GO2的PPO、TS方法下的backflip等动作的训练与部署

    GitHub · Python · 15 stars · 4 forks · +2 stars in 24 hours · Trending score 0.82

  12. 12
    lok-i/vibe

    Post-training humanoid whole-body trackers for perceptive control tasks

    GitHub · Python · 77 stars · 7 forks · +2 stars in 24 hours · Trending score 0.76

  13. 13
    EMI-Group/evorl

    EvoRL is a fully GPU-accelerated framework for Evolutionary Reinforcement Learning, implemented with JAX. It supports Reinforcement Learning (RL), Evolutionary Computation (EC), Evolution-guided Reinforcement Learning (ERL), AutoRL, and seamless integration with GPU-optimized simulation environments.

    GitHub · Python · 338 stars · 40 forks · +2 stars in 24 hours · Trending score 0.75

  14. 14
    guyue-maple1314/lingshu-ros2_quadruped_inspection

    灵枢巡检机器人 LingShu Inspector · 基于 ROS 2 三层架构(C++/Python/JavaScript)的四足机械狗巡检项目,覆盖 9 项核心技术

    GitHub · C++ · 14 stars · 2 forks · +2 stars in 24 hours · Trending score 0.73

  15. 15
    darshmenon/quadruped-robotics-stack

    Unitree Go2 quadruped stack: PPO locomotion in MuJoCo and Gazebo Harmonic, ROS2 CHAMP and Quad-SDK NMPC walkers, stair climbing, 3D LiDAR SLAM and RKO-LIO odometry, multi-terrain worlds

    GitHub · C++ · 34 stars · 8 forks · 0 stars in 24 hours · Trending score 0.36

  16. 16
    V01dMur10c/awesome-agent-rl-environments

    A curated list of training & evaluation environments for LLM/VLM agents (SWE-Gym, GEM, RAGEN, AgentGym, WebArena, OSWorld, ToolBench…). Updated weekly.

    GitHub · 12 stars · 5 forks · 0 stars in 24 hours · Trending score 0.17

  17. 17
    hbofz/NeSLE

    An NES emulator that runs as a CUDA kernel, one console per thread

    GitHub · Python · 36 stars · 2 forks · 0 stars in 24 hours · Trending score 0.12

  18. 18
    tterrasson/retrograd

    Run and Fine-tune GGUF models, with LoRA or full weights, from SFT to agentic GRPO

    GitHub · Rust · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.06

  19. 19
    0bserver07/Study-Reinforcement-Learning

    RL study guide — foundations through RLHF, DPO, GRPO, RLVR, agentic RL, and offline RL. Hand-written CS294 notes, 34 lecture drafts, 9 tested exercises, citations that resolve.

    GitHub · Python · 168 stars · 37 forks · 0 stars in 24 hours · Trending score 0.05

  20. 20
    ChuaCheowHuan/gym-continuousDoubleAuction

    A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.

    GitHub · Python · 155 stars · 33 forks · 0 stars in 24 hours · Trending score 0.01

  21. 21
    godka/Pensieve-PPO

    The simplest implementation of Pensieve (SIGCOMM' 17) via state-of-the-art RL algorithms, including PPO, DQN, SAC, and support for both TensorFlow and PyTorch.

    GitHub · DIGITAL Command Language · 92 stars · 40 forks · 0 stars in 24 hours · Trending score 0.00

  22. 22
    smtmRadu/DeepUnity

    An open source deep learning library for Unity.

    GitHub · C# · 18 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  23. 23
    hscspring/post-training-atlas

    An opinionated atlas of model post-training across modalities: RL, rewards, alignment, distillation, adaptation, agents, and their connections.

    GitHub · Python · 79 stars · 6 forks · 0 stars in 24 hours · Trending score 0.00

  24. 24
    curieuxjy/go2_dreamwaq

    Go2 quadruped locomotion with unofficial DreamWaQ implementation for rough terrain walking

    GitHub · Python · 39 stars · 6 forks · 0 stars in 24 hours · Trending score 0.00