Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/E2365192-8D33-48EE-8069-2097118F293B | - |
| Αναγνωριστικό | https://doi.org/10.1007/3-540-46014-4_23 | - |
| Αναγνωριστικό | https://users.cs.duke.edu/~parr/setn02.pdf | - |
| Γλώσσα | en | - |
| Μέγεθος | 12 pages | en |
| Τίτλος | Least-squares methods in reinforcement learning for control | en |
| Δημιουργός | Lagoudakis Michael | en |
| Δημιουργός | Λαγουδακης Μιχαηλ | el |
| Δημιουργός | Parr Ronald | en |
| Δημιουργός | Littman Michael L. | en |
| Περίληψη | Least-squares methods have been successfully used for prediction problems in the context of reinforcement learning, but little has been done in extending these methods to control problems. This paper presents an overview of our research efforts in using least-squares techniques for control. In our early attempts, we considered a direct extension of the Least-Squares Temporal Difference (LSTD) algorithm in the spirit of Q-learning. Later, an effort to remedy some limitations of this algorithm (approximation bias, poor sample utilization) led to the Least- Squares Policy Iteration (LSPI) algorithm, which is a form of model-free approximate policy iteration and makes efficient use of training samples collected in any arbitrary manner. The algorithms are demonstrated on a variety of learning domains, including algorithm selection, inverted pendulum balancing, bicycle balancing and riding, multiagent learning in factored domains, and, recently, on two-player zero-sum Markov games and the game of Tetris. | en |
| Τύπος | Πλήρης Δημοσίευση σε Συνέδριο | el |
| Τύπος | Conference Full Paper | en |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by-nc-nd/4.0/ | en |
| Ημερομηνία | 2015-11-17 | - |
| Ημερομηνία Δημοσίευσης | 2002 | - |
| Βιβλιογραφική Αναφορά | M. Lagoudakis , R. Parr , M. Littman ," Least-Squares Methods in Reinforcement Learning for Control," in 2002 Proceedings of the 2nd Hellenic Conference on Artificial Intelligence (SETN), pp. 249-260, doi: 10.1007/3-540-46014-4_23 | en |
Copyright © DIAS 2013
