Optimistic agents are asymptotically optimal

Loading...
Thumbnail Image

Date

Authors

Sunehag, Peter
Hutter, Marcus

Journal Title

Journal ISSN

Volume Title

Publisher

Springer Verlag

Abstract

We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic case we provide finite error bounds.

Description

Citation

Source

Book Title

AI 2012: Advances in Artificial Intelligence: 25th Australasian Joint Conference, Sydney, Australia, December 4-7, 2012. Proceedings

Entity type

Access Statement

License Rights

Restricted until