ログイン
言語:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

{"_buckets": {"deposit": "da5c445e-cfd9-4255-a273-f9347fd846f1"}, "_deposit": {"created_by": 17, "id": "2002686", "owner": "17", "owners": [17], "owners_ext": {"displayname": "repository", "username": "repository"}, "pid": {"revision_id": 0, "type": "depid", "value": "2002686"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:02002686", "sets": ["322"]}, "author_link": [], "item_1615768549627": {"attribute_name": "出版タイプ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_9_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2022-01", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "322", "bibliographicPageStart": "312", "bibliographicVolumeNumber": "52", "bibliographic_titles": [{"bibliographic_title": "IEEE Transactions on Cybernetics", "bibliographic_titleLang": "en"}]}]}, "item_9_description_4": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "Path integral policy improvement (PI^2) is known to be an efficient reinforcement learning algorithm, particularly, if the target system is a high-dimensional dynamical system. However, PI^2 , and its existing extensions, have adjustable parameters, on which the efficiency depends significantly. This article proposes an extension of PI^2 that adjusts all of the critical parameters automatically. Motion acquisition tasks for three different types of simulated legged robots were performed to test the efficacy of the proposed algorithm. The results show that the proposed method cannot only eliminate the burden on the user to set the parameters appropriately but also improve the optimization performance significantly. For one of the acquired motions, a real robot experiment was conducted to show the validity of the motion.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_9_publisher_32": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "IEEE", "subitem_publisher_language": "en"}]}, "item_9_relation_43": {"attribute_name": "関連情報", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.1109/TCYB.2020.2983923", "subitem_relation_type_select": "DOI"}}]}, "item_9_rights_12": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "“© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”", "subitem_rights_language": "en"}]}, "item_9_source_id_7": {"attribute_name": "収録物識別子", "attribute_value_mlt": [{"subitem_source_identifier": "2168-2267", "subitem_source_identifier_type": "PISSN"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "open access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_abf2"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Yamamoto, Kosuke", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Ariizumi, Ryo", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Hayakawa, Tomohiro", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Matsuno, Fumitoshi", "creatorNameLang": "en"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2022-05-09"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "FINAL_VERSION.pdf", "filesize": [{"value": "991 KB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "mimetype": "application/pdf", "size": 991000.0, "url": {"objectType": "fulltext", "url": "https://nagoya.repo.nii.ac.jp/record/2002686/files/FINAL_VERSION.pdf"}, "version_id": "98b9d18d-d061-48a0-91b8-ff978b3a7430"}]}, "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": "Path Integral Policy Improvement With Population Adaptation", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Path Integral Policy Improvement With Population Adaptation", "subitem_title_language": "en"}]}, "item_type_id": "40001", "owner": "17", "path": ["322"], "permalink_uri": "http://hdl.handle.net/2237/0002002686", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2022-05-09"}, "publish_date": "2022-05-09", "publish_status": "0", "recid": "2002686", "relation": {}, "relation_version_is_last": true, "title": ["Path Integral Policy Improvement With Population Adaptation"], "weko_shared_id": -1}
  1. B200 工学部/工学研究科
  2. B200a 雑誌掲載論文
  3. 学術雑誌

Path Integral Policy Improvement With Population Adaptation

http://hdl.handle.net/2237/0002002686
http://hdl.handle.net/2237/0002002686
945ef155-9c06-4949-9b19-0910e9194826
名前 / ファイル ライセンス アクション
FINAL_VERSION.pdf FINAL_VERSION.pdf (991 KB)
Item type itemtype_ver1(1)
公開日 2022-05-09
タイトル
タイトル Path Integral Policy Improvement With Population Adaptation
言語 en
著者 Yamamoto, Kosuke

× Yamamoto, Kosuke

en Yamamoto, Kosuke

Search repository
Ariizumi, Ryo

× Ariizumi, Ryo

en Ariizumi, Ryo

Search repository
Hayakawa, Tomohiro

× Hayakawa, Tomohiro

en Hayakawa, Tomohiro

Search repository
Matsuno, Fumitoshi

× Matsuno, Fumitoshi

en Matsuno, Fumitoshi

Search repository
アクセス権
アクセス権 open access
アクセス権URI http://purl.org/coar/access_right/c_abf2
権利
言語 en
権利情報 “© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
内容記述
内容記述 Path integral policy improvement (PI^2) is known to be an efficient reinforcement learning algorithm, particularly, if the target system is a high-dimensional dynamical system. However, PI^2 , and its existing extensions, have adjustable parameters, on which the efficiency depends significantly. This article proposes an extension of PI^2 that adjusts all of the critical parameters automatically. Motion acquisition tasks for three different types of simulated legged robots were performed to test the efficacy of the proposed algorithm. The results show that the proposed method cannot only eliminate the burden on the user to set the parameters appropriately but also improve the optimization performance significantly. For one of the acquired motions, a real robot experiment was conducted to show the validity of the motion.
言語 en
内容記述タイプ Abstract
出版者
言語 en
出版者 IEEE
言語
言語 eng
資源タイプ
資源タイプresource http://purl.org/coar/resource_type/c_6501
タイプ journal article
出版タイプ
出版タイプ AM
出版タイプResource http://purl.org/coar/version/c_ab4af688f83e57aa
関連情報
関連タイプ isVersionOf
識別子タイプ DOI
関連識別子 https://doi.org/10.1109/TCYB.2020.2983923
収録物識別子
収録物識別子タイプ PISSN
収録物識別子 2168-2267
書誌情報 en : IEEE Transactions on Cybernetics

巻 52, 号 1, p. 312-322, 発行日 2022-01
戻る
0
views
See details
Views

Versions

Ver.1 2022-05-09 05:47:17.682889
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Cite as

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3


Powered by WEKO3