WEKO3
アイテム
{"_buckets": {"deposit": "664224a7-4704-4720-9f73-19983d2772ed"}, "_deposit": {"created_by": 26, "id": "1546", "owners": [26], "pid": {"revision_id": 0, "type": "depid", "value": "1546"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00001546", "sets": ["26", "68"]}, "author_link": ["9355", "9358", "9356", "9357"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2015-03-03", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "3", "bibliographicPageStart": "e0115620", "bibliographicVolumeNumber": "10", "bibliographic_titles": [{}, {"bibliographic_title": "PLOS ONE", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Nakano, Takashi"}], "nameIdentifiers": [{"nameIdentifier": "9355", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Otsuka, Makoto"}], "nameIdentifiers": [{"nameIdentifier": "9356", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Yoshimoto, Junichiro"}], "nameIdentifiers": [{"nameIdentifier": "9357", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Doya, Kenji"}], "nameIdentifiers": [{"nameIdentifier": "9358", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach.", "subitem_description_type": "Other"}]}, "item_10001_publisher_8": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_publisher": "PLOS"}]}, "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/25734662", "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/10.1371/journal.pone.0115620", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_16": {"attribute_name": "情報源", "attribute_value_mlt": [{"subitem_relation_name": [{"subitem_relation_name_text": "http://creativecommons.org/licenses/by/4.0/"}]}]}, "item_10001_relation_17": {"attribute_name": "Related site", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0115620", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2015 Nakano et al."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1932-6203", "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": "2020-06-15"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "Nakano-2015-A spiking neural network model of.pdf", "filesize": [{"value": "6.8 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "Creative Commons Attribution 4.0 International\n(http://creativecommons.org/licenses/by/4.0/)", "licensetype": "license_free", "mimetype": "application/pdf", "size": 6800000.0, "url": {"label": "Nakano-2015-A spiking neural network model of", "url": "https://oist.repo.nii.ac.jp/record/1546/files/Nakano-2015-A spiking neural network model of.pdf"}, "version_id": "fbe56568-c9f0-4307-8d7e-c2d891a15d89"}]}, "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 Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "A Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "26", "path": ["26", "68"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/1546", "pubdate": {"attribute_name": "公開日", "attribute_value": "2020-06-15"}, "publish_date": "2020-06-15", "publish_status": "0", "recid": "1546", "relation": {}, "relation_version_is_last": true, "title": ["A Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity"], "weko_shared_id": 26}
A Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity
https://oist.repo.nii.ac.jp/records/1546
https://oist.repo.nii.ac.jp/records/154638d81f22-bc2b-4e5f-927c-97053b167c9f
名前 / ファイル | ライセンス | アクション |
---|---|---|
Nakano-2015-A spiking neural network model of (6.8 MB)
|
Creative Commons Attribution 4.0 International
(http://creativecommons.org/licenses/by/4.0/) |
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2020-06-15 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | A Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity | |||||
言語 | ||||||
言語 | eng | |||||
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) |
Nakano, Takashi
× Nakano, Takashi× Otsuka, Makoto× Yoshimoto, Junichiro× Doya, Kenji |
|||||
書誌情報 |
en : PLOS ONE 巻 10, 号 3, p. e0115620, 発行日 2015-03-03 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach. | |||||
出版者 | ||||||
出版者 | PLOS | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1932-6203 | |||||
PubMed番号 | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | PMID | |||||
関連識別子 | info:pmid/25734662 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1371/journal.pone.0115620 | |||||
権利 | ||||||
権利情報 | © 2015 Nakano et al. | |||||
情報源 | ||||||
関連名称 | http://creativecommons.org/licenses/by/4.0/ | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0115620 | |||||
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 |