Reinforcement Learning for Dexterity Transfer Between Manipulators

Learning complex manipulation skills with robotic arms is a challenging problem in Reinforcement Learning. Training policies from scratch is often timeconsuming and normally infeasible when using real robots. Existing techniques solve this issue by leveraging human priors in the form of shaped rewar...

Full description

Saved in:
Bibliographic details
Main Author: Rapisarda, Carlo
Format: Publication
Language: English
Place of publication: KTH, Skolan för elektroteknik och datavetenskap (EECS) 01.01.2019
Data of publication: 2019-01-01
Online Access: available in Bonn?
Database: OpenAIRE (Open Access)
Database information Databases - DBIS