gordicaleksa/pytorch-learn-reinforcement-learning

A collection of various RL algorithms like policy gradients, DQN and PPO. The goal of this repo will be to make it a go-to resource for learning about RL. How to visualize, debug and solve RL problems. I've additionally included playground.py for learning more about OpenAI gym, etc.

47
/ 100
Emerging

This project offers PyTorch implementations of fundamental reinforcement learning algorithms like DQN, designed for those looking to understand and experiment with RL. It takes in game states (like Atari frames) and outputs a trained agent capable of playing those games. This is ideal for researchers, students, or practitioners who are learning about or building AI agents for decision-making tasks in simulated environments.

161 stars. No commits in the last 6 months.

Use this if you want to learn about reinforcement learning by experimenting with well-structured, memory-efficient implementations of classic algorithms and need robust visualization and debugging tools.

Not ideal if you need a production-ready, fully optimized RL agent for deployment without hands-on learning or debugging.

AI-research game-AI algorithm-education agent-training deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

161

Forks

35

Language

Python

License

MIT

Last pushed

May 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gordicaleksa/pytorch-learn-reinforcement-learning"

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