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.

32
/ 100
Emerging

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.

robotics robot-training autonomous-systems robot-learning offline-reinforcement-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

32

Forks

3

Language

Python

License

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.