HackerPapers

arXiv:1210.0077cs.AI

Optimistic Agents are Asymptotically Optimal

Peter Sunehag, Marcus Hutter

HN submission. Found in a submission link or body. Submitters do not count as commenters in the main ranking; a submission is not an endorsement.

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.

arXiv comments
13 LaTeX pages
Journal reference
Proc. 25th Australasian Joint Conference on Artificial Intelligence (AusAI 2012) 15-26
DOI
Subjects
cs.AIArtificial Intelligence cs.LGMachine Learning

On Hacker News

No comments linking this paper were found in the collected sources. Found in 2 HN submissions from Jan 2017 to Aug 2019. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments0 threads

No comments linking this paper were found in the collected sources. Open submission discussions.

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.