inoryy/reaver
Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.
This is a framework for developing and testing AI agents that can learn to play real-time strategy games like StarCraft II. It provides tools to train an agent by feeding it game observations (like screen visuals) and evaluating its actions to improve performance over time. The primary users are AI researchers or hobbyists interested in deep reinforcement learning for game AI.
562 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are an AI researcher or enthusiast looking to train reinforcement learning agents to play StarCraft II or other simulated environments like Atari games or MuJoCo.
Not ideal if you need an actively maintained project or are looking for a plug-and-play AI to win games without delving into the underlying reinforcement learning mechanics.
Stars
562
Forks
87
Language
Python
License
MIT
Category
Last pushed
Nov 01, 2020
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/inoryy/reaver"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild