Multi-criteria Reinforcement Learning
Lists
Only you see this
Abstract
Ve cOllf:iider multi- criteria f:iequent,ial decision making problems where the vcctor-"valucd evaluations arc compared by a given, fixed total ordering. Condit.ions for the opt.irnality of statiOIl<-l,r}' p()lichs ;-weI the Bellman opti malit,y equatio n a re given for a. speci al, but. important class of problems ''v hell the eval uation of policies can be computed for the criteria, independently of each other. The anal)'sis requires special cafC as t.he t.opol ag,Y int.roduced by polnL\visc convergence a.ncl the or<1cr- topology introduced by the prefer ence order arc in general incompatible. Re inf orcement. learning algorithms are proposed and analY7,ed.
BibTeX
@inproceedings{gabor1998multi,
author = {Zoltán Gábor and Zsolt Kalmár and Csaba Szepesvári},
title = {{Multi-criteria Reinforcement Learning}},
booktitle = {International Conference on Machine Learning},
year = {1998},
url = {https://openreview.net/forum?id=rybkMjWOZB},
}Loading related content...