Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/E504E59F-683F-49F8-9E3F-41D26D6FC513 | - |
| Αναγνωριστικό | http://eprints.ulster.ac.uk/21032/1/AAMAS2012_0089_7016861a9.pdf | - |
| Γλώσσα | en | - |
| Μέγεθος | 8 pages | en |
| Τίτλος | Decentralized bayesian reinforcement learning for online agent collaboration | en |
| Δημιουργός | Parr G. | en |
| Δημιουργός | Farinelli A. | en |
| Δημιουργός | Rogers A. | en |
| Δημιουργός | Chalkiadakis Georgios | en |
| Δημιουργός | Χαλκιαδακης Γεωργιος | el |
| Δημιουργός | Jennings N. R. | en |
| Δημιουργός | McClean S. | en |
| Δημιουργός | Teacy W. T. L. | en |
| Εκδότης | International Foundation for Autonomous Agents and Multiagent Systems | en |
| Εκδότης | IFAAMS | en |
| Περίληψη | Solving complex but structured problems in a decentralized manner via multiagent collaboration has received much attention in recent years. This is natural, as on one hand, multiagent systems usu- ally possess a structure that determines the allowable interactions among the agents; and on the other hand, the single most pressing need in a cooperative multiagent system is to coordinate the local policies of autonomous agents with restricted capabilities to serve a system-wide goal. The presence of uncertainty makes this even more challenging, as the agents face the additional need to learn the unknown environment parameters while forming (and follow- ing) local policies in an online fashion. In this paper, we provide the first Bayesian reinforcement learning (BRL) approach for dis- tributed coordination and learning in a cooperative multiagent sys- tem by devising two solutions to this type of problem. More specif- ically, we show how the Value of Perfect Information (VPI) can be used to perform efficient decentralised exploration in both model- based and model-free BRL, and in the latter case, provide a closed form solution for VPI, correcting a decade old result by Dearden, Friedman and Russell. To evaluate these solutions, we present ex- perimental results comparing their relative merits, and demonstrate empirically that both solutions outperform an existing multiagent learning method, representative of the state-of-the-art. | en |
| Τύπος | Πλήρης Δημοσίευση σε Συνέδριο | el |
| Τύπος | Conference Full Paper | en |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
| Ημερομηνία | 2015-09-30 | - |
| Ημερομηνία Δημοσίευσης | 2012 | - |
| Θεματική Κατηγορία | Multiagent learning | en |
| Θεματική Κατηγορία | Bayesian techniques | en |
| Θεματική Κατηγορία | Uncertainty | en |
| Βιβλιογραφική Αναφορά | W. T. L. Leacy, G. Chalkiadakis, A. Farinelli, A. Rogers, N. R. Jennings, S. McClean and G. Parr, "Decentralized bayesian reinforcement learning for online agent collaboration," presented at 11th International Conference on Autonomous Agents and Multiagent Systems, Valencia, Spain, 2012. | en |
Copyright © DIAS 2013
