WEKO3
アイテム
{"_buckets": {"deposit": "ffd5de62-d1db-4886-bb21-c78f2ae5af99"}, "_deposit": {"created_by": 27, "id": "210", "owners": [27], "pid": {"revision_id": 0, "type": "depid", "value": "210"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00000210", "sets": ["26"]}, "author_link": ["540", "539", "479"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2017-01-23", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "15", "bibliographicPageStart": "1", "bibliographicVolumeNumber": "11", "bibliographic_titles": [{}, {"bibliographic_title": "Frontiers in Neurorobotics", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Wang, Jiexin"}], "nameIdentifiers": [{"nameIdentifier": "539", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Uchibe, Eiji"}], "nameIdentifiers": [{"nameIdentifier": "540", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Doya, Kenji"}], "nameIdentifiers": [{"nameIdentifier": "479", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "EM-based policy search methods estimate a lower bound of the expected return from the histories of episodes and iteratively update the policy parameters using the maximum of a lower bound of expected return, which makes gradient calculation and learning rate tuning unnecessary. Previous algorithms like Policy learning by Weighting Exploration with the Returns, Fitness Expectation Maximization, and EM-based Policy Hyperparameter Exploration implemented the mechanisms to discard useless low-return episodes either implicitly or using a fixed baseline determined by the experimenter. In this paper, we propose an adaptive baseline method to discard worse samples from the reward history and examine different baselines, including the mean, and multiples of SDs from the mean. The simulation results of benchmark tasks of pendulum swing up and cart-pole balancing, and standing up and balancing of a two-wheeled smartphone robot showed improved performances. We further implemented the adaptive baseline with mean in our two-wheeled smartphone robot hardware to test its performance in the standing up and balancing task, and a view-based approaching task. Our results showed that with adaptive baseline, the method outperformed the previous algorithms and achieved faster, and more precise behaviors at a higher successful rate.", "subitem_description_type": "Other"}]}, "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/28167910", "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/10.3389/fnbot.2017.00001", "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": "http://journal.frontiersin.org/article/10.3389/fnbot.2017.00001/full", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "©2017 Wang, Uchibe, and Doya."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1662-5218", "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": "2017-12-28"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "fnbot-11-00001.pdf", "filesize": [{"value": "16.2 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": 16200000.0, "url": {"label": "fnbot-11-00001", "url": "https://oist.repo.nii.ac.jp/record/210/files/fnbot-11-00001.pdf"}, "version_id": "d3ab5aea-2f50-4b38-af82-14f5b38e24b3"}]}, "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": "Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer"}, {"subitem_title": "Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "27", "path": ["26"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/210", "pubdate": {"attribute_name": "公開日", "attribute_value": "2017-12-28"}, "publish_date": "2017-12-28", "publish_status": "0", "recid": "210", "relation": {}, "relation_version_is_last": true, "title": ["Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer"], "weko_shared_id": 27}
Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer
https://oist.repo.nii.ac.jp/records/210
https://oist.repo.nii.ac.jp/records/2101363e170-840a-46df-866f-0cb8eba44ec6
名前 / ファイル | ライセンス | アクション |
---|---|---|
fnbot-11-00001 (16.2 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 | 2017-12-28 | |||||
タイトル | ||||||
タイトル | Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer | |||||
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) |
Wang, Jiexin
× Wang, Jiexin× Uchibe, Eiji× Doya, Kenji |
|||||
書誌情報 |
en : Frontiers in Neurorobotics 巻 11, 号 1, p. 1-15, 発行日 2017-01-23 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | EM-based policy search methods estimate a lower bound of the expected return from the histories of episodes and iteratively update the policy parameters using the maximum of a lower bound of expected return, which makes gradient calculation and learning rate tuning unnecessary. Previous algorithms like Policy learning by Weighting Exploration with the Returns, Fitness Expectation Maximization, and EM-based Policy Hyperparameter Exploration implemented the mechanisms to discard useless low-return episodes either implicitly or using a fixed baseline determined by the experimenter. In this paper, we propose an adaptive baseline method to discard worse samples from the reward history and examine different baselines, including the mean, and multiples of SDs from the mean. The simulation results of benchmark tasks of pendulum swing up and cart-pole balancing, and standing up and balancing of a two-wheeled smartphone robot showed improved performances. We further implemented the adaptive baseline with mean in our two-wheeled smartphone robot hardware to test its performance in the standing up and balancing task, and a view-based approaching task. Our results showed that with adaptive baseline, the method outperformed the previous algorithms and achieved faster, and more precise behaviors at a higher successful rate. | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1662-5218 | |||||
PubMed番号 | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | PMID | |||||
関連識別子 | info:pmid/28167910 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.3389/fnbot.2017.00001 | |||||
権利 | ||||||
権利情報 | ©2017 Wang, Uchibe, and Doya. | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | http://journal.frontiersin.org/article/10.3389/fnbot.2017.00001/full | |||||
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 |