Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
RL algorithms, environments, simulators and decision-making systems.
Signals: reinforcement-learning, deep-reinforcement-learning, rl, gymnasium, openai-gym, multi-agent-reinforcement-learning, imitation-learning
664 results
Reinforcement Learning environments based on the 1993 game Doom :godmode:
A library of reinforcement learning components and agents
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Mastering Diverse Domains through World Models
Simple and easily configurable grid world environments for reinforcement learning
Puffing up reinforcement learning
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
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
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
Distributed Reinforcement Learning accelerated by Lightning Fabric
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.
A unified framework for easy fine-tuning in Flow-Matching models
Uni-Agent is a framework for training long-horizon agents.
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
Multi-Agent Reinforcement Learning with JAX
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Official reinforcement learning environment for demand response and load shaping
A language agent gym with challenging scientific tasks
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
24,545 repositories in the index in total.
