Home Projects cleanrl
cleanrl

cleanrl

by vwxyzjn · GitHub

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

View on GitHub
⭐ Stars
10.1k
🍴 Forks
1.1k
🔥 Trending
+12 this week
📜 License
License not specified
📅 Created
2019
🔄 Last commit
3 mo ago
🏷️ Category
a2c
💻 Language
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
cleanrl — GitHub preview card
📈 Star history
10.12k10.07k
2026-07-042026-07-22
📄 About

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Frequently asked questions

What is cleanrl?

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Is cleanrl open source?

cleanrl is an open-source project.

Is cleanrl free?

Yes. cleanrl is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?
olud.ai badge — cleanrl

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=vwxyzjn-cleanrl)](https://olud.ai/project/vwxyzjn-cleanrl.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.