takuseno/minerva
An out-of-the-box GUI tool for offline deep reinforcement learning
This tool helps anyone, even non-programmers, use advanced deep reinforcement learning to solve problems. You provide a dataset of observations and actions, and it trains a powerful decision-making policy. The output is a trained policy that can be exported for use in other systems. It's designed for data scientists, researchers, or practitioners looking to leverage AI for automated decision-making.
102 stars. No commits in the last 6 months.
Use this if you have existing interaction data and want to train an AI to make optimal decisions based on that data, without needing to write code.
Not ideal if you need a reinforcement learning system that interacts directly with an environment in real-time or if you require extensive custom algorithm development.
Stars
102
Forks
10
Language
JavaScript
License
MIT
Category
Last pushed
May 29, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/takuseno/minerva"
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