diambra/arena
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation
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.
Stars
361
Forks
27
Language
Python
License
—
Category
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.
Higher-rated alternatives
facebookresearch/habitat-lab
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
facebookresearch/ELF
An End-To-End, Lightweight and Flexible Platform for Game Research
utra-robosoccer/soccerbot
Soccer playing robot representing Canada from University of Toronto
Project-DC/pygeneses
A PyTorch based DeepRL framework to train and study artificial species in bio-inspired environments.
alex-petrenko/megaverse
High-throughput simulation platform for Artificial Intelligence reseach