Asap7772/PTR
This repository contains the implementation of the PTR algorithm described in the paper: Pre-Training for Robots: Leveraging Diverse Multitask Data via Offline Reinforcement Learning.
This project helps robotics engineers and researchers train robots more effectively by leveraging diverse, pre-recorded data from various tasks. You input existing robot interaction datasets, and it outputs a more robustly trained robot policy capable of performing new, unseen tasks with better generalization. This is for professionals developing and deploying autonomous robotic systems.
No commits in the last 6 months.
Use this if you need to pre-train a robot using a variety of offline datasets to improve its ability to perform multiple tasks or adapt to new ones.
Not ideal if you are looking for a real-time, online robot learning solution or if you don't have access to diverse offline robotic interaction data.
Stars
32
Forks
3
Language
Python
License
—
Category
Last pushed
Oct 26, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Asap7772/PTR"
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