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

@article{Kormushev:2011,
author = {Kormushev, P and Nomoto, K and Dong, F and Hirota, K},
journal = {Cybernetics and Information Technologies},
pages = {42--59},
title = {Time hopping technique for faster reinforcement learning in simulations},
url = {http://hdl.handle.net/10044/1/26062},
volume = {11},
year = {2011}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - A technique called Time Hopping is proposed for speeding up reinforcement learning algorithms. It is applicable to continuous optimization problems running in computer simulations. Making shortcuts in time by hopping between distant states combined with off-policy reinforcement learning allows the technique to maintain higher learning rate. Experiments on a simulated biped crawling robot confirm that Time Hopping can accelerate the learning process more than seven times.
AU - Kormushev,P
AU - Nomoto,K
AU - Dong,F
AU - Hirota,K
EP - 59
PY - 2011///
SN - 1311-9702
SP - 42
TI - Time hopping technique for faster reinforcement learning in simulations
T2 - Cybernetics and Information Technologies
UR - http://hdl.handle.net/10044/1/26062
VL - 11
ER -