Asymptotically Optimal Agents

Lattimore, Tor, Hutter, Marcus Artificial Intelligence 

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.

Duplicate Docs Excel Report

None found

Similar Docs  Excel Report  more

None found