Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Value function approximation in zero–sum Markov games

Lagoudakis Michael, Parr,R.

Απλή Εγγραφή

URIhttp://purl.tuc.gr/dl/dias/2F95F669-B215-44BD-90AF-6176BD490AA9-
Αναγνωριστικόhttp://arxiv.org/ftp/arxiv/papers/1301/1301.0580.pdf-
Γλώσσαen-
Μέγεθος10 pagesen
ΤίτλοςValue function approximation in zero–sum Markov gamesen
ΔημιουργόςLagoudakis Michaelen
ΔημιουργόςΛαγουδακης Μιχαηλel
ΔημιουργόςParr,R.en
ΠερίληψηThis paper investigates value function approximation in the context of zero-sum Markov games, which can be viewed as a generalization of the Markov decision process (MDP) framework to the two-agent case. We generalize error bounds from MDPs to Markov games and describe generalizations of reinforcement learning algorithms to Markov games. We present a generalization of the optimal stopping problem to a two-player simultaneous move Markov game. For this special problem, we provide stronger bounds and can guarantee convergence for LSTD and temporal difference learning with linear value function approximation. We demonstrate the viability of value function approximation for Markov games by using the Least squares policy iteration (LSPI) algorithm to learn good policies for a soccer domain and a flow control problem. en
ΤύποςΠλήρης Δημοσίευση σε Συνέδριοel
ΤύποςConference Full Paperen
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2015-11-13-
Ημερομηνία Δημοσίευσης2002-
Θεματική ΚατηγορίαArtificial Intelligenceen
Βιβλιογραφική ΑναφοράM.G. Lagoudakis and R. Parr. (2002, Aug.). Value function approximation in zero–sum Markov games. [Online]. Available: http://arxiv.org/ftp/arxiv/papers/1301/1301.0580.pdfen

Υπηρεσίες

Στατιστικά

 

Copyright © DIAS 2013