lucaslingle/pytorch_rl2
Implementation of 'RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning'
This project helps operations engineers, researchers, and anyone designing autonomous systems to quickly train AI agents that can adapt to new, similar environments without extensive retraining. It takes in a set of related environment simulations and outputs an agent capable of learning a new task efficiently from a few trials. This is ideal for those working with various bandit problems or Markov Decision Processes.
No commits in the last 6 months.
Use this if you need an AI agent that can rapidly learn optimal behavior in slightly different but related environments, especially when traditional reinforcement learning requires too much re-training.
Not ideal if your environments are vastly different from each other or if you are not comfortable with foundational machine learning concepts and Python development.
Stars
72
Forks
11
Language
Python
License
—
Category
Last pushed
Jan 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lucaslingle/pytorch_rl2"
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