nadavbh12/Retro-Learning-Environment
The Retro Learning Environment (RLE) -- a learning framework for AI
This is a learning framework for AI. It allows you to train and evaluate AI algorithms against classic console games like Mortal Kombat and Super Mario All Stars, using the game's screen as input. This is for AI researchers or hobbyists interested in developing and testing game-playing AI agents.
186 stars. No commits in the last 6 months.
Use this if you are developing or studying AI agents that learn to play retro video games from visual input.
Not ideal if you are looking for a currently maintained or actively developed environment, as this project has been succeeded by OpenAI's Gym-retro.
Stars
186
Forks
41
Language
C++
License
—
Category
Last pushed
Jun 06, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nadavbh12/Retro-Learning-Environment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Farama-Foundation/stable-retro
Retro games for Reinforcement Learning Research
MatPoliquin/stable-retro-scripts
Train models on retro games. AI vs AI contest. Pytorch C++ plugin for RetroArch that let you...
svpino/cs7641-assignment4
CS7641 - Machine Learning - Assignment 4 - Markov Decision Processes
Avalon-Benchmark/avalon
A 3D video game environment and benchmark designed from scratch for reinforcement learning research
abhinavcreed13/ai-reinforcement-learning
This project will implement value iteration and Q-learning. It will first test agents on...