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{Leonetti:2012,
author = {Leonetti, M and Kormushev, P and Sagratella, S},
journal = {Cybernetics and Information Technologies},
pages = {53--65},
title = {Combining local and global direct derivative-free optimization for reinforcement learning},
url = {http://hdl.handle.net/10044/1/26053},
volume = {12},
year = {2012}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - We consider the problem of optimization in policy space for reinforcement learning. While a plethora of methods have been applied to this problem, only a narrow category of them proved feasible in robotics. We consider the peculiar characteristics of reinforcement learning in robotics, and devise a combination of two algorithms from the literature of derivative-free optimization. The proposed combination is well suited for robotics, as it involves both off-line learning in simulation and on-line learning in the real environment. We demonstrate our approach on a real-world task, where an Autonomous Underwater Vehicle has to survey a target area under potentially unknown environment conditions. We start from a given controller, which can perform the task under foreseeable conditions, and make it adaptive to the actual environment.
AU - Leonetti,M
AU - Kormushev,P
AU - Sagratella,S
EP - 65
PY - 2012///
SN - 1311-9702
SP - 53
TI - Combining local and global direct derivative-free optimization for reinforcement learning
T2 - Cybernetics and Information Technologies
UR - http://hdl.handle.net/10044/1/26053
VL - 12
ER -