 |
    |
Optimistic Agents Are Asymptotically Optimal
Peter Sunehag and Marcus Hutter
Research School of Computer Science, Australian National University, Canberra, Australiapeter.sunehag@anu.edu.au
marcus.hutter@anu.edu.au
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.
Keywords: Reinforcement Learning, Optimism, Optimality
LNAI 7691, p. 15 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012