On Measuring the Impact of Human Actions in the Machine Learning of a Board Game's Playing Policies

Simple item page
dc.creatorKalles, Dimitris
dc.date2006-11-30
dc.date.accessioned2026-07-07T07:31:48Z
dc.date.available2026-07-07T07:31:48Z
dc.descriptionWe investigate systematically the impact of human intervention in the training of computer players in a strategy board game. In that game, computer players utilise reinforcement learning with neural networks for evolving their playing strategies and demonstrate a slow learning speed. Human intervention can significantly enhance learning performance, but carry-ing it out systematically seems to be more of a problem of an integrated game development environment as opposed to automatic evolutionary learning.
dc.descriptionContains 19 pages, 10 figures, 8 tables. Submitted to a journal
dc.identifierhttps://arxiv.org/abs/cs/0611163
dc.identifierhttp://arxiv.org/abs/cs/0611163
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/118885
dc.subjectArtificial Intelligence
dc.subjectComputer Science and Game Theory
dc.subjectNeural and Evolutionary Computing
dc.titleOn Measuring the Impact of Human Actions in the Machine Learning of a Board Game's Playing Policies
dc.typetext

Files

Collections

arXiv