WEKO3
アイテム
{"_buckets": {"deposit": "45497c03-6d89-411a-b050-b087271ac831"}, "_deposit": {"created_by": 33, "id": "2714", "owners": [33], "pid": {"revision_id": 0, "type": "depid", "value": "2714"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00002714", "sets": ["25"]}, "author_link": ["17509", "17511", "17510"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2022-03-21", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "258", "bibliographicPageStart": "237", "bibliographicVolumeNumber": "150", "bibliographic_titles": [{}, {"bibliographic_title": "Neural Networks", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Verduzco-Flores, Sergio"}], "nameIdentifiers": [{"nameIdentifier": "17509", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Dorrell, William"}], "nameIdentifiers": [{"nameIdentifier": "17510", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "De Schutter, Erik"}], "nameIdentifiers": [{"nameIdentifier": "17511", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "In this paper we explore a neural control architecture that is both biologically plausible, and capable of fully autonomous learning. It consists of feedback controllers that learn to achieve a desired state by selecting the errors that should drive them. This selection happens through a family of differential Hebbian learning rules that, through interaction with the environment, can learn to control systems where the error responds monotonically to the control signal. We next show that in a more general case, neural reinforcement learning can be coupled with a feedback controller to reduce errors that arise non-monotonically from the control signal. The use of feedback control can reduce the complexity of the reinforcement learning problem, because only a desired value must be learned, with the controller handling the details of how it is reached. This makes the function to be learned simpler, potentially allowing learning of more complex actions. We use simple examples to illustrate our approach, and discuss how it could be extended to hierarchical architectures.", "subitem_description_type": "Other"}]}, "item_10001_publisher_8": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_publisher": "Elsevier Ltd."}]}, "item_10001_relation_13": {"attribute_name": "PubMedNo.", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:pmid/35325677", "subitem_relation_type_select": "PMID"}}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:doi/10.1016/j.neunet.2022.03.002", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_17": {"attribute_name": "Related site", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://www.sciencedirect.com/science/article/pii/S0893608022000727?via%3Dihub", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2022 The Authors."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0893-6080", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"attribute_name": "Author\u0027s flag", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2022-07-20"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "1-s2.0-S0893608022000727-main.pdf", "filesize": [{"value": "3.2 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/)", "licensetype": "license_free", "mimetype": "application/pdf", "size": 3200000.0, "url": {"label": "1-s2.0-S0893608022000727-main", "url": "https://oist.repo.nii.ac.jp/record/2714/files/1-s2.0-S0893608022000727-main.pdf"}, "version_id": "0fd3e876-0731-41f6-8b7c-7a86ead274a9"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Synaptic plasticity", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Motor control", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Reinforcement learning", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Feedback control", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "A differential Hebbian framework for biologically-plausible motor control", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "A differential Hebbian framework for biologically-plausible motor control", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "33", "path": ["25"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/2714", "pubdate": {"attribute_name": "公開日", "attribute_value": "2022-07-20"}, "publish_date": "2022-07-20", "publish_status": "0", "recid": "2714", "relation": {}, "relation_version_is_last": true, "title": ["A differential Hebbian framework for biologically-plausible motor control"], "weko_shared_id": 33}
A differential Hebbian framework for biologically-plausible motor control
https://oist.repo.nii.ac.jp/records/2714
https://oist.repo.nii.ac.jp/records/2714893c2867-e648-476b-beb5-30404e523265
名前 / ファイル | ライセンス | アクション |
---|---|---|
1-s2.0-S0893608022000727-main (3.2 MB)
|
Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/)
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2022-07-20 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | A differential Hebbian framework for biologically-plausible motor control | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Synaptic plasticity | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Motor control | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Reinforcement learning | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Feedback control | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
著者(英) |
Verduzco-Flores, Sergio
× Verduzco-Flores, Sergio× Dorrell, William× De Schutter, Erik |
|||||
書誌情報 |
en : Neural Networks 巻 150, p. 237-258, 発行日 2022-03-21 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | In this paper we explore a neural control architecture that is both biologically plausible, and capable of fully autonomous learning. It consists of feedback controllers that learn to achieve a desired state by selecting the errors that should drive them. This selection happens through a family of differential Hebbian learning rules that, through interaction with the environment, can learn to control systems where the error responds monotonically to the control signal. We next show that in a more general case, neural reinforcement learning can be coupled with a feedback controller to reduce errors that arise non-monotonically from the control signal. The use of feedback control can reduce the complexity of the reinforcement learning problem, because only a desired value must be learned, with the controller handling the details of how it is reached. This makes the function to be learned simpler, potentially allowing learning of more complex actions. We use simple examples to illustrate our approach, and discuss how it could be extended to hierarchical architectures. | |||||
出版者 | ||||||
出版者 | Elsevier Ltd. | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 0893-6080 | |||||
PubMed番号 | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | PMID | |||||
関連識別子 | info:pmid/35325677 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1016/j.neunet.2022.03.002 | |||||
権利 | ||||||
権利情報 | © 2022 The Authors. | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://www.sciencedirect.com/science/article/pii/S0893608022000727?via%3Dihub | |||||
著者版フラグ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 |