Asymptotically Optimal Agents

07/27/2011

∙

by   Tor Lattimore, et al.

∙

0

∙

share

Artificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.