A divided and prioritized experience replay approach for streaming regression
dc.contributor.author | Arnø, Mikkel Leite | |
dc.contributor.author | Godhavn, John-Morten | |
dc.contributor.author | Aamo, Ole Morten | |
dc.date.accessioned | 2023-01-11T08:34:31Z | |
dc.date.available | 2023-01-11T08:34:31Z | |
dc.date.created | 2021-12-03T00:16:06Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | MethodsX. 2021, 8 1-14. | en_US |
dc.identifier.issn | 2215-0161 | |
dc.identifier.uri | https://hdl.handle.net/11250/3042557 | |
dc.description.abstract | In the streaming learning setting, an agent is presented with a data stream on which to learn from in an online fashion. A common problem is catastrophic forgetting of old knowledge due to updates to the model. Mitigating catastrophic forgetting has received a lot of attention, and a variety of methods exist to solve this problem. In this paper, we present a divided and prioritized experience replay approach for streaming regression, in which relevant observations are retained in the replay, and extra focus is added to poorly estimated observations through prioritization. Using a real-world dataset, the method is compared to the standard sliding window approach. A statistical power analysis is performed, showing how our approach improves performance on rare, important events at a trade-off in performance for more common observations. Close inspections of the dataset are provided, with emphasis on areas where the standard approach fails. A rephrasing of the problem to a binary classification problem is performed to separate common and rare, important events. These results provide an added perspective regarding the improvement made on rare events. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Elsevier Science | en_US |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.title | A divided and prioritized experience replay approach for streaming regression | en_US |
dc.title.alternative | A divided and prioritized experience replay approach for streaming regression | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.source.pagenumber | 1-14 | en_US |
dc.source.volume | 8 | en_US |
dc.source.journal | MethodsX | en_US |
dc.identifier.doi | 10.1016/j.mex.2021.101571 | |
dc.identifier.cristin | 1963897 | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 |