A Policy Improvement Algorithm for Some Classes of Stochastic Games

Bourque, Matthew J.

A Policy Improvement Algorithm for Some Classes of Stochastic Games

https://hdl.handle.net/10027/10178
Open external identifier URL

thesis

posted on 2013-10-24, 00:00 authored by Matthew J. Bourque

Stochastic games generalize Markov decision processes and repeated games. We give a policy improvement algorithm for additive reward, addi- tive transition (ARAT) zero-sum two-player stochastic games for both discounted and average payoffs. The class of ARAT games includes perfect information games.

History

Language

en

Advisor

Raghavan, T.E.S.

Department

Mathematics, Statistics, and Computer Science

Degree Grantor

University of Illinois at Chicago

Degree Level

Doctoral

Committee Member

Brown, Joel Friedland, Shmuel Gaubert, Stéphane Verschelde, Jan Yang, Jie

Submitted date

2013-08

Issue date

2013-10-24

Usage metrics

Keywords

game theory stochastic games Markov decision processes policy improvement perfect information additive reward additive transition

Licence

In Copyright

A Policy Improvement Algorithm for Some Classes of Stochastic Games

History

Language

Advisor

Department

Degree Grantor

Degree Level

Committee Member

Submitted date

Issue date

Usage metrics

Categories

Keywords

Licence

Exports