vwxyzjn/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
This tool helps researchers and deep reinforcement learning (DRL) practitioners implement and understand DRL algorithms. It provides single, self-contained Python files for popular algorithms like PPO and DQN. You input an algorithm file and an environment (like an Atari game), and it outputs a trained DRL agent along with performance logs and gameplay videos. It is designed for those who want to dive deep into the specific implementation details of DRL algorithms.
9,286 stars. No commits in the last 6 months.
Use this if you are a researcher or DRL practitioner looking to understand, reproduce, or modify the fine-grained implementation details of specific deep reinforcement learning algorithms.
Not ideal if you need a modular DRL library for building complex, custom reinforcement learning systems where you want to import components rather than study standalone implementations.
Stars
9,286
Forks
1,015
Language
Python
License
—
Category
Last pushed
Jul 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vwxyzjn/cleanrl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild