dc.contributor.author | Hegdal, Sondre Steinsland | |
dc.contributor.author | Kofod-Petersen, Anders | |
dc.date.accessioned | 2020-05-13T12:22:16Z | |
dc.date.available | 2020-05-13T12:22:16Z | |
dc.date.created | 2019-09-12T16:45:46Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | CEUR Workshop Proceedings. 2019, 2567 18-28. | en_US |
dc.identifier.issn | 1613-0073 | |
dc.identifier.uri | https://hdl.handle.net/11250/2654269 | |
dc.description.abstract | This paper proposes a Case-based Reasoning (CBR) and Artificial Neural Network (ANN) hybrid solution for dynamic problems. In this solution, a CBR system chooses between several expert neural networks for a given case/problem. These neural networks are Recurrent Neural Networks, which are trained using Deep Q-Learning (DQN). The system was tested on the game Mega Man 2 for the NES, and is compared to how a single recurrent neural network performed. The results collected outperforms the basic ANN that it was compared against, and provides a good base for future research on the model. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | CEUR Workshop Proceedings | en_US |
dc.relation.uri | http://ceur-ws.org/Vol-2567/ | |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.title | A CBR-ANN hybrid for dynamic environments | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.source.pagenumber | 18-28 | en_US |
dc.source.volume | 2567 | en_US |
dc.source.journal | CEUR Workshop Proceedings | en_US |
dc.identifier.cristin | 1724142 | |
dc.description.localcode | Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). | en_US |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |