Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/2F95F669-B215-44BD-90AF-6176BD490AA9 | - |
| Αναγνωριστικό | http://arxiv.org/ftp/arxiv/papers/1301/1301.0580.pdf | - |
| Γλώσσα | en | - |
| Μέγεθος | 10 pages | en |
| Τίτλος | Value function approximation in zero–sum Markov games | en |
| Δημιουργός | Lagoudakis Michael | en |
| Δημιουργός | Λαγουδακης Μιχαηλ | el |
| Δημιουργός | Parr,R. | en |
| Περίληψη | This 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 |
| Τύπος | Πλήρης Δημοσίευση σε Συνέδριο | el |
| Τύπος | Conference Full Paper | en |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
| Ημερομηνία | 2015-11-13 | - |
| Ημερομηνία Δημοσίευσης | 2002 | - |
| Θεματική Κατηγορία | Artificial Intelligence | en |
| Βιβλιογραφική Αναφορά | M.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.pdf | en |
Copyright © DIAS 2013
