English

Asymptotically Optimal Agents

Artificial Intelligence 2012-02-10 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1107.5537,
  title  = {Asymptotically Optimal Agents},
  author = {Tor Lattimore and Marcus Hutter},
  journal= {arXiv preprint arXiv:1107.5537},
  year   = {2012}
}

Comments

21 LaTeX pages

R2 v1 2026-06-21T18:43:03.671Z