C
cleanrl
vwxyzjn/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
★10.2kstars
Python
NOASSERTION
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Learning & Resources category, core strengths: a2c/actor-critic
Who made it?Maintained by vwxyzjn team, 10.2K⭐ on GitHub, #255 out of 3640 in Learning & Resources
Why does it exist?As the Learning & Resources landscape evolved, the vwxyzjn team identified the need for better a2c solutions. cleanrl was created to simplify actor-critic workflows.
What can it do?Key use cases: advantage-actor-critic, ale, atari
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/vwxyzjn/cleanrl | 官网 http://docs.cleanrl.dev
🔗 github.com/vwxyzjn/cleanrl | 官网 http://docs.cleanrl.dev
Topics
a2cactor-criticadvantage-actor-criticaleatarideep-learningdeep-reinforcement-learninggymmachine-learningphasic-policy-gradientppoproximal-policy-optimizationpythonpytorchreinforcement-learningwandb