Asymptotically Optimal Agents
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.
|Collections||ANU Research Publications|
|Source:||Lecture Notes in Artificial Intelligence 6925|
|01_Lattimore_Asymptotically_Optimal_A_2011.pdf||259.84 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.