DeNA/HandyRL
HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.
This framework helps competitive gamers, AI researchers, or data scientists efficiently train AI agents to excel in complex games or simulations. By providing your game environment, it processes game states and actions to produce a powerful AI agent capable of winning against other agents or players. It focuses on creating strong, winning AIs for competitive scenarios.
304 stars. No commits in the last 6 months.
Use this if you need to quickly develop and train a high-performing AI agent for a competitive game or a simulated environment, especially if large-scale distributed training is required.
Not ideal if your primary goal is to develop foundational reinforcement learning algorithms from scratch rather than apply existing, proven methods to achieve a strong agent.
Stars
304
Forks
44
Language
Python
License
—
Category
Last pushed
Feb 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DeNA/HandyRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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