danijar/mindpark
Testbed for deep reinforcement learning
This tool helps researchers and AI developers prototype, test, and compare deep reinforcement learning algorithms. You provide the algorithm definition and the simulated environment (like a game), and it generates metrics and statistics on how well the AI learns and performs. It's designed for those building and evaluating AI agents that learn by interacting with their surroundings.
162 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a researcher or AI developer working on deep reinforcement learning and need a systematic way to test and compare different learning algorithms in various environments.
Not ideal if you are looking for a pre-trained reinforcement learning agent to deploy directly or if your primary focus is not on developing and evaluating the algorithms themselves.
Stars
162
Forks
29
Language
Python
License
GPL-3.0
Category
Last pushed
Jun 12, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danijar/mindpark"
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