English

Optimistic Agents are Asymptotically Optimal

Artificial Intelligence 2013-05-17 v1 Machine Learning

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

Cite

@article{arxiv.1210.0077,
  title  = {Optimistic Agents are Asymptotically Optimal},
  author = {Peter Sunehag and Marcus Hutter},
  journal= {arXiv preprint arXiv:1210.0077},
  year   = {2013}
}

Comments

13 LaTeX pages

R2 v1 2026-06-21T22:13:15.411Z