Zoekopdracht:
faculteit: "FNWI" en publicatiejaar: "2008"
| Auteurs | C. Dimitrakakis, M.G. Lagoudakis | | Titel | Rollout sampling approximate policy iteration |
| Tijdschrift | MACH LEARN |
| Jaargang | 72 |
| Jaar | 2008 |
| Nummer | 3 |
| Pagina's | 157-171 |
| ISSN | 08856125 |
| Faculteit | Faculteit der Natuurwetenschappen, Wiskunde en Informatica |
| Instituut/afd. | FNWI: Informatics Institute (II) |
| Samenvatting | Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervised learning problem. This paper proposes variants of an improved policy iteration scheme which addresses the core sampling problem in evaluating a policy through simulation as a multi-armed bandit machine. The resulting algorithm offers comparable performance to the previous algorithm achieved, however, with significantly less computational effort. An order of magnitude improvement is demonstrated experimentally in two standard reinforcement learning domains: inverted pendulum and mountain-car. |
| Soort document | Artikel |
| Download bestand | |
| Document finder |
|
Gebruik dit adres om naar deze pagina te linken: http://dare.uva.nl/record/289909
Vraag/opmerking over dit recordMail aan een collega
Toevoegen aan bewaarset
|