Kaixhin/Atari

Persistent advantage learning dueling double DQN for the Arcade Learning Environment

49
/ 100
Emerging

This project helps researchers and practitioners in artificial intelligence train and evaluate reinforcement learning agents on classic Atari games or custom simulation environments. You provide game ROMs or a defined environment, and it outputs a trained agent that can play the game, along with performance metrics and visual saliency maps. This tool is designed for AI researchers, machine learning engineers, and data scientists working on advanced reinforcement learning algorithms.

263 stars. No commits in the last 6 months.

Use this if you are developing or testing new deep reinforcement learning algorithms and need a robust framework to train agents on video game environments.

Not ideal if you are a casual gamer looking for an AI opponent or if you need a simple, off-the-shelf solution for game automation.

reinforcement-learning deep-learning AI-research game-AI agent-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

263

Forks

72

Language

Lua

License

MIT

Last pushed

Feb 08, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Kaixhin/Atari"

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