Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning

File Description SizeFormat 
Kormushev_JACIII-2009.pdfAccepted version516.96 kBAdobe PDFView/Open
Title: Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning
Authors: Kormushev, P
Nomoto, K
Dong, F
Hirota, K
Item Type: Internet Publication
Abstract: A mechanism called Eligibility Propagation is proposed to speed up the Time Hopping technique used for faster Reinforcement Learning in simulations. Eligibility Propagation provides for Time Hopping similar abilities to what eligibility traces provide for conventional Reinforcement Learning. It propagates values from one state to all of its temporal predecessors using a state transitions graph. Experiments on a simulated biped crawling robot confirm that Eligibility Propagation accelerates the learning process more than 3 times.
Issue Date: 3-Apr-2009
URI: http://hdl.handle.net/10044/1/26076
Copyright Statement: © 2009 The Authors
Publication Status: Unpublished
Publisher URL: http://kormushev.com/papers/Kormushev_JACIII-2009.pdf
Appears in Collections:Dyson School of Design Engineering



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

Creative Commonsx