Imperial College London

DrPetarKormushev

Faculty of EngineeringDyson School of Design Engineering

Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 9235p.kormushev Website

 
 
//

Location

 

10-12 Prince's GardensSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Kormushev:2009,
author = {Kormushev, P and Dong, F and Hirota, K},
title = {Probability redistribution using time hopping for reinforcement learning},
url = {http://kormushev.com/papers/Kormushev_ISIS-2009.pdf},
year = {2009}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - —A method for using the Time Hopping techniqueas a tool for probability redistribution is proposed. Applied toreinforcement learning in a simulation, it is able to re-shape thestate probability distribution of the underlying Markov decisionprocess as desired. This is achieved by modifying the targetselection strategy of Time Hopping appropriately. Experimentswith a robot maze reinforcement learning problem show that themethod improves the exploration efficiency by re-shaping thestate probability distribution to an almost uniform distribution.
AU - Kormushev,P
AU - Dong,F
AU - Hirota,K
PY - 2009///
TI - Probability redistribution using time hopping for reinforcement learning
UR - http://kormushev.com/papers/Kormushev_ISIS-2009.pdf
UR - http://hdl.handle.net/10044/1/26089
ER -