opendilab/DI-engine
quality grade C, 62 out of 100OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
- stars
- 3.6k
- stars gained this week
- +5this week
- forks, open issues and contributors
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
653 results
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
Check out the new game server:
Minimal and Clean Reinforcement Learning Examples
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Massively Parallel Deep Reinforcement Learning. 🔥
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI
Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
A Next-Generation Training Engine Built for Ultra-Large MoE Models
Repo for the Deep Reinforcement Learning Nanodegree program
StarCraft II Learning Environment
强化学习中文教程(蘑菇书🍄),在线阅读地址:https://datawhalechina.github.io/easy-rl/
Python Implementation of Reinforcement Learning: An Introduction
Machine learning, in numpy
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
Understanding R1-Zero-Like Training: A Critical Perspective
Latest Advances on System-2 Reasoning
[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Scalable RL solution for advanced reasoning of language models
Implementation of all RL algorithms in a simpler way
Implementation of papers in 100 lines of code.
MuZero
An elegant PyTorch deep reinforcement learning library.
Implementation of the paper "Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning"
24,523 repositories in the index in total.