astier/model-free-episodic-control
Model-Free-Episodic-Control implementation.
This project helps reinforcement learning researchers and practitioners experiment with Model-Free Episodic Control. It takes raw environmental observations (like frames from an Atari game) and produces a trained agent capable of playing the game, along with performance metrics. It's intended for researchers or students exploring episodic control algorithms for sequential decision-making tasks.
No commits in the last 6 months.
Use this if you need to implement and test the Model-Free Episodic Control algorithm (without the VAE component) for tasks like game playing or robotic control.
Not ideal if you require the Variational Autoencoder (VAE) component of the original paper or need a pre-packaged solution for immediate application in a production environment.
Stars
17
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jun 03, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/astier/model-free-episodic-control"
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