Kaixhin/Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

50
/ 100
Established

This project helps machine learning researchers and practitioners experiment with advanced deep reinforcement learning techniques. It takes configurations for various improvements (like Double DQN or Prioritised Experience Replay) as input and outputs trained models capable of playing Atari games, along with performance results. It's designed for those exploring or applying cutting-edge RL algorithms.

1,661 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or student who wants to quickly test and combine state-of-the-art deep reinforcement learning algorithms for tasks like game AI.

Not ideal if you are looking for a plug-and-play solution to integrate AI into a business application or if you are new to deep learning concepts.

reinforcement-learning deep-learning game-ai atari-games algorithm-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,661

Forks

292

Language

Python

License

MIT

Last pushed

Jan 13, 2022

Commits (30d)

0

Get this data via API

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

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