The many faces of optimism - Extended version

Simple item page
dc.creatorSzita, István
dc.creatorLőrincz, András
dc.date2008-10-20
dc.date.accessioned2026-07-07T10:11:38Z
dc.date.available2026-07-07T10:11:38Z
dc.descriptionThe exploration-exploitation dilemma has been an intriguing and unsolved problem within the framework of reinforcement learning. "Optimism in the face of uncertainty" and model building play central roles in advanced exploration methods. Here, we integrate several concepts and obtain a fast and simple algorithm. We show that the proposed algorithm finds a near-optimal policy in polynomial time, and give experimental evidence that it is robust and efficient compared to its ascendants.
dc.descriptionExtended version of the homonymous ICML'08 paper, with proofs
dc.identifierhttps://arxiv.org/abs/0810.3451
dc.identifierhttp://arxiv.org/abs/0810.3451
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/171924
dc.subjectArtificial Intelligence
dc.subjectComputational Complexity
dc.subjectMachine Learning
dc.titleThe many faces of optimism - Extended version
dc.typetext

Files

Collections

arXiv