denisyarats/proto
Proto-RL: Reinforcement Learning with Prototypical Representations
This project helps machine learning researchers develop intelligent agents that learn new tasks more efficiently. It takes raw environmental data from simulations or real-world scenarios and outputs a trained agent capable of performing a specific task. Reinforcement learning researchers and practitioners who want to build agents that generalize well to new environments would use this.
No commits in the last 6 months.
Use this if you are a reinforcement learning researcher looking to pre-train agents on various tasks to improve their learning speed and adaptability.
Not ideal if you are looking for a ready-to-use, pre-trained agent for a specific real-world application without delving into agent training methodologies.
Stars
86
Forks
13
Language
Python
License
MIT
Category
Last pushed
Jun 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/denisyarats/proto"
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