XinJingHao/DRL-Pytorch

Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

41
/ 100
Emerging

This project provides pre-built, robust implementations of various deep reinforcement learning (DRL) algorithms, like Q-learning, PPO, and SAC. It helps AI researchers and practitioners rapidly experiment with different DRL approaches by offering a clean, unified codebase. You input a problem (e.g., a robot learning to walk in a simulation) and get out trained models capable of making optimal decisions in that environment.

3,306 stars. No commits in the last 6 months.

Use this if you are an AI researcher or robotics engineer who needs to quickly test and compare established deep reinforcement learning algorithms for controlling autonomous systems or agents in simulations.

Not ideal if you are looking for a plug-and-play solution without any programming knowledge or if you need to deploy these algorithms directly into complex, real-world physical systems without further engineering.

AI-research robotics-control autonomous-agents simulation-training reinforcement-learning
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

3,306

Forks

388

Language

Python

License

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/XinJingHao/DRL-Pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.