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
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
FinRL®: Financial Reinforcement Learning. 🔥
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
Train transformer language models with reinforcement learning.
Multimodal RL training framework for diffusion & omni models
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
An interface library for RL post training with environments.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Simulation of spiking neural networks (SNNs) using PyTorch.
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
SkyRL: A Modular Full-stack RL Library for LLMs
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
[RSS 2026] Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion. Official implementation of RSS 2026.
Uplift modeling and causal inference with machine learning algorithms
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
24,545 repositories in the index in total.
