Multi-Task Policy Search for Robotics

File Description SizeFormat 
icra2014_final_short.pdfAccepted version3.02 MBAdobe PDFDownload
Title: Multi-Task Policy Search for Robotics
Author(s): Deisenroth, MP
Englert, P
Peters, J
Fox, D
Item Type: Conference Paper
Abstract: © 2014 IEEE.Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for continuous task variations, requiring more principled approaches to share and transfer knowledge among similar tasks. We present a novel approach for learning a nonlinear feedback policy that generalizes across multiple tasks. The key idea is to define a parametrized policy as a function of both the state and the task, which allows learning a single policy that generalizes across multiple known and unknown tasks. Applications of our novel approach to reinforcement and imitation learning in realrobot experiments are shown.
Publication Date: 1-Jun-2014
URI: http://hdl.handle.net/10044/1/12812
Copyright Statement: © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Conference Name: 2014 IEEE International Conference on Robotics and Automation (ICRA 2014)
Conference Location: Hong Kong, China
Publication Status: Accepted
Start Date: 2014-05-31
Finish Date: 2014-06-07
Conference Place: Hong Kong, China
Appears in Collections:Computing



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons