diambra/arena

DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation

40
/ 100
Emerging

This platform provides a collection of classic fighting video game environments to help you experiment with and research Reinforcement Learning (RL) agents. You input your RL algorithms, and the platform outputs trained agents capable of playing these games in various modes, including single-player, competitive multi-agent, or even against human players. This is designed for AI researchers and practitioners focused on developing and evaluating RL systems.

361 stars. No commits in the last 6 months.

Use this if you are an AI researcher or developer looking for a standardized, high-quality, and challenging environment to train and test your Reinforcement Learning algorithms on arcade-style fighting games.

Not ideal if you are looking for a platform to develop AI for non-gaming applications or if your primary interest is casual gaming rather than AI research.

Reinforcement Learning AI Research Game AI Development Multi-Agent Systems Machine Learning Experimentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

361

Forks

27

Language

Python

License

Last pushed

Jun 11, 2024

Commits (30d)

0

Get this data via API

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

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