domain: reinforcement-learning
265 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| verl-project/verl verl (Volcano Engine Reinforcement Learning) is a flexible, production-ready RL post-training library for large language models, open-sourc… | 84 | 23145 | active |
| trycua/cua Cua is an open-source framework for computer-use agents, providing background desktop drivers, disposable GUI sandboxes, cross-OS fleets (L… | 83 | 21922 | active |
| Unity-Technologies/ml-agents The Unity Machine Learning Agents Toolkit (ML-Agents) lets Unity games and simulations serve as environments for training intelligent agent… | 69 | 19647 | active |
| huggingface/trl TRL is a Hugging Face library for post-training transformer language models with techniques like Supervised Fine-Tuning (SFT), GRPO, DPO, K… | 99 | 19155 | active |
| microsoft/agent-lightning Agent Lightning is a lightweight (~3,500-line) agentic reinforcement learning framework from Microsoft for training LLM-powered agents with… | 85 | 17863 | active |
| FinRL FinRL is the first open-source deep reinforcement learning framework for financial markets, providing end-to-end pipelines to build, train,… | 76 | 16108 | active |
| bulletphysics/bullet3 Bullet Physics SDK is a C++ library providing real-time collision detection and rigid/soft body multi-physics simulation, with Python bindi… | 44 | 14700 | stable |
| DLR-RM/stable-baselines3 Stable Baselines3 is a Python library providing reliable, well-tested PyTorch implementations of reinforcement learning algorithms with a u… | 91 | 13728 | stable |
| Farama-Foundation/Gymnasium Gymnasium is a Python library providing a standard API for single-agent reinforcement learning environments, maintained by the Farama Found… | 88 | 12408 | stable |
| thu-ml/tianshou Tianshou is a modular, high-performance deep reinforcement learning library built on pure PyTorch and Gymnasium. It offers both low-level h… | 72 | 10943 | active |
| google/dopamine Dopamine is a research framework from Google for fast prototyping of reinforcement learning algorithms, built around a small, easily readab… | 56 | 10900 | active |
| OpenPipe/ART ART (Agent Reinforcement Trainer) is an open-source Python framework for training multi-step LLM agents using reinforcement learning techni… | 86 | 10665 | active |
| vwxyzjn/cleanrl CleanRL is a deep reinforcement learning library providing high-quality, single-file implementations of algorithms like PPO, DQN, DDPG, TD3… | 58 | 10326 | active |
| OpenRLHF/OpenRLHF OpenRLHF is a high-performance, production-ready open-source RLHF framework built on Ray + vLLM + DeepSpeed for scalable reinforcement lear… | 89 | 9956 | active |
| VowpalWabbit/vowpal_wabbit Vowpal Wabbit is a fast, open-source machine learning system focused on online, active, and interactive learning, including contextual band… | 90 | 8706 | active |
| THUDM/slime slime is an open-source LLM post-training framework for reinforcement learning scaling, connecting Megatron-based training with SGLang-base… | 80 | 8261 | active |
| isaac-sim/IsaacLab Isaac Lab is a GPU-accelerated open-source framework for robot learning built on NVIDIA Isaac Sim, unifying workflows like reinforcement le… | 92 | 7966 | active |
| openai/gym Gym is a Python toolkit for developing and comparing reinforcement learning algorithms via a standard API between learning algorithms and e… | 10 | 37251 | maintenance |
| MineDojo/Voyager Voyager is an open-source LLM-powered embodied agent that plays Minecraft through GPT-4, using an automatic curriculum, an ever-growing ski… | 29 | 7160 | active |
| tensortrade-org/tensortrade TensorTrade is an open-source Python framework for building, training, and evaluating reinforcement learning agents for algorithmic trading… | 64 | 7067 | active |
| PufferAI/PufferLib PufferLib is a fast, open-source reinforcement learning library that trains tiny, super-human models in seconds, achieving 1M+ environment … | 81 | 6306 | active |
| rllm-org/rllm rLLM is an open-source Python framework for training language agents with reinforcement learning, supporting any agent harness (Claude Code… | 77 | 5803 | active |
| areal-project/AReaL AReaL is a large-scale asynchronous reinforcement learning system that bridges foundation model training with agent-based applications, sup… | 87 | 5696 | active |
| Gen-Verse/OpenClaw-RL OpenClaw-RL is a framework for training personalized AI agents through reinforcement learning using natural conversation as feedback. It us… | 52 | 5655 | active |
| google-deepmind/open_spiel OpenSpiel is a collection of game environments and reinforcement learning/search/planning algorithms for research in general RL and multiag… | 98 | 5435 | active |
| PeterGriffinJin/Search-R1 Search-R1 is an open-source reinforcement learning framework for training LLMs that interleave reasoning with search engine calls, built on… | 43 | 5328 | active |
| Baekalfen/PyBoy PyBoy is a Game Boy and Game Boy Color emulator written in Python, usable both as a standalone terminal application and as an embeddable Py… | 89 | 5193 | active |
| hiyouga/EasyR1 EasyR1 is an efficient, scalable reinforcement learning training framework for large language models and vision-language models, built as a… | 65 | 5129 | active |
| google-deepmind/dm_control Google DeepMind's Python stack for physics-based simulation and reinforcement learning environments built on the MuJoCo physics engine. It … | 94 | 4672 | stable |
| RLinf/RLinf RLinf is an open-source, flexible and scalable reinforcement learning training infrastructure for embodied AI (vision-language-action model… | 74 | 4655 | active |
| TencentCloudADP/youtu-agent Youtu-Agent is a Python framework for building, running, and evaluating autonomous LLM agents, supporting ReAct-style single agents and pla… | 57 | 4604 | active |
| PrimeIntellect-ai/verifiers verifiers is a Python library for creating environments to train and evaluate large language models with reinforcement learning. It integra… | 88 | 4559 | active |
| AI4Finance-Foundation/ElegantRL ElegantRL is a lightweight, modular deep reinforcement learning library built on PyTorch that implements core model-free RL algorithms (PPO… | 53 | 4355 | active |
| lucas-maes/le-wm LeWorldModel (LeWM) is the official PyTorch codebase for a JEPA-based world model that trains stably end-to-end from raw pixels using only … | 52 | 4344 | active |
| OpenManus/OpenManus-RL OpenManus-RL is an open-source project for reinforcement-learning-based tuning of LLM agents, built on the verl training framework. It prov… | 46 | 4155 | active |
| google-deepmind/acme Acme is a Python library of reinforcement learning building blocks and agent implementations from DeepMind. It provides readable reference … | 67 | 4050 | active |
| openai/baselines OpenAI Baselines is a collection of high-quality reference implementations of reinforcement learning algorithms such as DQN, PPO, and ACKTR… | 32 | 16764 | maintenance |
| danijar/dreamerv3 A Python/JAX reimplementation of DreamerV3, a model-based reinforcement learning algorithm that learns a world model and trains an actor-cr… | 69 | 3704 | active |
| opendilab/DI-engine DI-engine is an open-source reinforcement learning framework from OpenDILab that provides comprehensive implementations of deep RL algorith… | 48 | 3638 | active |
| pytorch/rl TorchRL is a PyTorch-native library of composable primitives for building reinforcement learning systems, including environments, policies,… | 97 | 3538 | active |
| apirrone/Open_Duck_Mini Open Duck Mini is an open-source project to build a miniature (~42cm) bipedal robot inspired by Disney's BDX droid, with a bill of material… | 53 | 3521 | active |
| unitreerobotics/unitree_rl_gym A reinforcement learning gym environment for training locomotion policies on Unitree robots (Go2, H1, H1_2, G1) using Isaac Gym and Mujoco.… | 42 | 3516 | active |
| Farama-Foundation/PettingZoo PettingZoo is a Python library providing a standard API for multi-agent reinforcement learning environments, analogous to Gymnasium but for… | 89 | 3498 | active |
| PaddlePaddle/PARL PARL is a flexible, high-performance reinforcement learning framework built on PaddlePaddle, providing Model/Algorithm/Agent abstractions a… | 41 | 3453 | active |
| XinJingHao/DRL-Pytorch A unified PyTorch implementation collection of popular deep reinforcement learning algorithms including DQN variants, PPO, DDPG, TD3, SAC, … | 44 | 3436 | active |
| alibaba/ROLL ROLL is an open-source reinforcement learning library from Alibaba for training large language models at scale, supporting algorithms like … | 78 | 3374 | active |
| Farama-Foundation/HighwayEnv HighwayEnv is a collection of Gymnasium environments for autonomous driving and tactical decision-making tasks, covering scenarios like hig… | 94 | 3298 | active |
| mani-skill/ManiSkill ManiSkill is an open-source GPU-parallelized robotics simulation framework and benchmark built on SAPIEN, focused on manipulation skills. I… | 91 | 3264 | active |
| LeelaChessZero/lc0 Lc0 is an open-source, UCI-compliant chess engine that plays chess using neural networks trained via AlphaZero-style self-play reinforcemen… | 65 | 3193 | active |
| TradeMaster-NTU/TradeMaster TradeMaster is an open-source Python platform for quantitative trading powered by reinforcement learning, covering the full pipeline of alg… | 34 | 3050 | active |
| tensorflow/agents TF-Agents is a TensorFlow-based Python library for building, training, and deploying reinforcement learning and contextual bandit algorithm… | 60 | 3025 | active |
| facebookresearch/Pearl Pearl is a production-ready reinforcement learning agent library developed by Meta's Applied Reinforcement Learning team. It provides modul… | 74 | 3024 | active |
| leggedrobotics/rsl_rl RSL-RL is a GPU-accelerated, lightweight reinforcement learning library for robotics research, featuring algorithms like PPO and Student-Te… | 97 | 2916 | active |
| eric-mitchell/direct-preference-optimization A reference implementation of Direct Preference Optimization (DPO) for training language models from human preference data, built on Huggin… | 29 | 2907 | stable |
| DLR-RM/rl-baselines3-zoo RL Baselines3 Zoo is a training framework for reinforcement learning agents built on Stable Baselines3. It provides CLI scripts for trainin… | 92 | 2870 | active |
| werner-duvaud/muzero-general A commented and documented PyTorch implementation of DeepMind's MuZero reinforcement learning algorithm, designed to be easily adapted to a… | 32 | 2861 | active |
| mujocolab/mjlab mjlab is a Python framework that combines Isaac Lab's manager-based API with MuJoCo Warp, a GPU-accelerated version of MuJoCo, for reinforc… | 85 | 2837 | active |
| mll-lab-nu/RAGEN RAGEN is a Python framework for training reasoning LLM agents with multi-turn reinforcement learning using the StarPO algorithm. It also pr… | 65 | 2778 | active |
| google-deepmind/mctx Mctx is a JAX-native Python library implementing Monte Carlo tree search algorithms such as AlphaZero, MuZero, and Gumbel MuZero. It suppor… | 83 | 2654 | active |
| ARISE-Initiative/robosuite robosuite is a modular simulation framework powered by the MuJoCo physics engine for robot learning, offering standardized benchmark enviro… | 72 | 2581 | active |
| EMI-Group/evox EvoX is a distributed GPU-accelerated framework for evolutionary computation, compatible with PyTorch and built on JAX. It provides 50+ evo… | 80 | 2526 | active |
| huggingface/OpenEnv OpenEnv is a Hugging Face framework for creating, deploying, and consuming isolated execution environments used in agentic reinforcement le… | 81 | 2521 | active |
| Farama-Foundation/Minigrid Minigrid is a Python library of lightweight, easily configurable discrete grid-world environments for reinforcement learning research, foll… | 82 | 2499 | active |
| Farama-Foundation/Arcade-Learning-Environment The Arcade Learning Environment (ALE) is a framework built on the Stella Atari 2600 emulator that lets researchers and hobbyists develop an… | 94 | 2448 | stable |
| Unakar/Logic-RL Logic-RL is a research framework that reproduces R1-Zero-style LLM reasoning via rule-based reinforcement learning (GRPO) on logic puzzles,… | 26 | 2448 | active |
| AminHP/gym-anytrading gym-anytrading is a collection of OpenAI Gym environments for developing and testing reinforcement learning-based trading algorithms in FOR… | 23 | 2386 | stable |
| Roboparty/roboto_origin A fully open-source DIY humanoid robot project (ROBOTO_ORIGIN) that can walk and run, including all hardware designs, electronics, training… | 60 | 2326 | active |
| google-deepmind/optax Optax is a gradient processing and optimization library for JAX, offering composable building blocks like optimizers and loss functions. It… | 82 | 2325 | stable |
| radixark/miles Miles is an open-source, enterprise-grade reinforcement learning framework for large-scale LLM and VLM post-training, forked from and co-ev… | 72 | 2263 | active |
| langfengQ/verl-agent verl-agent is an extension of the veRL framework for training LLM and VLM agents via reinforcement learning, featuring step-independent mul… | 56 | 2256 | active |
| xbpeng/MimicKit MimicKit is a lightweight Python framework providing a suite of motion imitation methods (DeepMimic, AMP, ASE, AWR, and others) for trainin… | 56 | 2254 | active |
| NovaSky-AI/SkyRL SkyRL is a modular full-stack reinforcement learning library for post-training large language models, combining a training framework (skyrl… | 80 | 2201 | active |
| galilai-group/stable-worldmodel A Python library providing a unified platform for reproducible world model research, covering data collection, training, and evaluation via… | 81 | 2156 | active |
| google-deepmind/pysc2 PySC2 is DeepMind's Python component of the StarCraft II Learning Environment, exposing Blizzard's StarCraft II Machine Learning API as a P… | 23 | 8307 | maintenance |
| google/trax Trax is an end-to-end deep learning library built on JAX and TensorFlow that focuses on clear code and speed, developed and maintained by t… | 10 | 8306 | maintenance |
| learnsyslab/gym-pybullet-drones A Python library providing PyBullet-based Gymnasium environments for simulating quadcopter control in single- and multi-agent reinforcement… | 67 | 2116 | active |
| LeCAR-Lab/ASAP ASAP is a two-stage framework for training agile humanoid whole-body skills by aligning simulation and real-world physics. It pre-trains mo… | 48 | 2100 | active |
| Open-Reasoner-Zero/Open-Reasoner-Zero Open-Reasoner-Zero is an open-source implementation of large-scale reinforcement learning training for reasoning-oriented language models, … | 31 | 2099 | active |
| eloialonso/diamond DIAMOND is a Python implementation of a reinforcement learning agent trained entirely inside a diffusion-based world model, presented as a … | 24 | 2096 | active |
| marlbenchmark/on-policy The official PyTorch implementation of Multi-Agent PPO (MAPPO), an on-policy reinforcement learning algorithm for cooperative multi-agent s… | 32 | 2085 | active |
| roboterax/humanoid-gym Humanoid-Gym is a reinforcement learning framework built on Nvidia Isaac Gym for training locomotion skills in humanoid robots, with emphas… | 27 | 2075 | active |
| lupantech/AgentFlow AgentFlow is a trainable, tool-integrated agentic framework that coordinates planner, executor, verifier, and generator modules through an … | 47 | 2017 | active |
| PrimeIntellect-ai/prime-rl prime-rl is a Python framework for large-scale, fully asynchronous reinforcement learning training of language models, built on FSDP2 for t… | 87 | 1975 | active |
| tensorlayer/TensorLayer TensorLayer is a TensorFlow-based deep learning and reinforcement learning library offering customizable neural layers for researchers and … | 23 | 7381 | maintenance |
| google-deepmind/lab DeepMind Lab is a customisable 3D learning environment built on Quake III Arena (ioquake3) that provides navigation and puzzle-solving task… | 23 | 7373 | maintenance |
| policy-gradient/GRPO-Zero A minimal from-scratch Python implementation of DeepSeek's GRPO (Group Relative Policy Optimization) algorithm for reinforcement learning t… | 27 | 1897 | active |
| fan-ziqi/robot_lab robot_lab is a reinforcement learning extension library for robots built on top of NVIDIA IsaacLab, providing preconfigured locomotion envi… | 73 | 1891 | active |
| BytedTsinghua-SIA/DAPO DAPO is an open-source reinforcement learning system for large-scale LLM training, released by ByteDance Seed and Tsinghua AIR. It implemen… | 29 | 1861 | active |
| openreasoner/openr OpenR is an open-source Python framework that integrates search, reinforcement learning, and process supervision to improve chain-of-though… | 23 | 1853 | active |
| PRIME-RL/SimpleVLA-RL SimpleVLA-RL is an open-source reinforcement learning framework for training Vision-Language-Action (VLA) models for robotic manipulation, … | 46 | 1834 | active |
| AgiBot X1 The inference module of the open-source AgiBot X1 humanoid robot software stack, providing model inference, platform drivers, and simulatio… | 28 | 1834 | active |
| RoboVerseOrg/RoboVerse RoboVerse is a unified platform, dataset, and benchmark for scalable and generalizable robot learning, providing tasks, robots, scenes, ass… | 68 | 1810 | active |
| chynl/snake A Python application that plays the game of Snake using two AI approaches: a graph-search algorithm based on Hamiltonian paths and shortest… | 67 | 1787 | active |
| microsoft/CyberBattleSim CyberBattleSim is a Python-based experimentation and research platform from Microsoft that simulates abstract enterprise network environmen… | 77 | 1784 | active |
| Simple-Efficient/RL-Factory RLFactory is a reinforcement learning post-training framework for training agentic LLM models, decoupling the environment from RL training … | 34 | 1780 | active |
| HumanCompatibleAI/imitation A Python library providing clean PyTorch implementations of imitation and reward learning algorithms such as Behavioral Cloning, DAgger, GA… | 23 | 1779 | active |
| HybridRobotics/berkeley-humanoid-lite Berkeley Humanoid Lite is the open-source codebase for a sub-$5,000 3D-printed humanoid robot platform from UC Berkeley. It includes Isaac … | 56 | 1681 | active |
| takuseno/d3rlpy d3rlpy is a Python library for offline and online deep reinforcement learning built on PyTorch, offering state-of-the-art algorithms throug… | 52 | 1679 | active |
| opendilab/LightZero LightZero is a lightweight, open-source Python toolkit that unifies Monte Carlo Tree Search (MCTS) with deep reinforcement learning, implem… | 67 | 1636 | active |
| AgentR1/Agent-R1 Agent-R1 is a modular Python framework for training LLM agents with end-to-end reinforcement learning. It models each interaction turn as a… | 65 | 1633 | active |
page 1 / 3 next →