{"_buckets": {"deposit": "3cbcac06-23e9-4d56-aad6-ea58a7f4b32a"}, "_deposit": {"id": "8954", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "8954"}, "status": "published"}, "_oai": {"id": "oai:kitami-it.repo.nii.ac.jp:00008954"}, "item_3_alternative_title_198": {"attribute_name": "\u305d\u306e\u4ed6\u306e\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_alternative_title": "(The Optimal Algorithms for the Reinforcement Learning Problem Separated into a Learning Period and a Control Period)"}]}, "item_3_biblio_info_186": {"attribute_name": "\u66f8\u8a8c\u60c5\u5831", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1998-04-15", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "4", "bibliographicPageEnd": "1126", "bibliographicPageStart": "1116", "bibliographicVolumeNumber": "39", "bibliographic_titles": [{"bibliographic_title": "\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u8ad6\u6587\u8a8c"}, {"bibliographic_title": "Transactions of Information Processing Society of Japan", "bibliographic_titleLang": "en"}]}]}, "item_3_description_184": {"attribute_name": "\u6284\u9332", "attribute_value_mlt": [{"subitem_description": "\u672c\u7814\u7a76\u3067\u306f\uff0c\u9077\u79fb\u78ba\u7387\u884c\u5217\u304c\u672a\u77e5\u3067\u3042\u308b\u3088\u3046\u306a\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b\u306b\u3088\u3063\u3066\u30e2\u30c7\u30eb\u5316\u3055\u308c\u3066\u3044\u308b\uff0c\u5b66\u7fd2\u671f\u9593\u3068\u5236\u5fa1\u671f\u9593\u306b\u5206\u5272\u3055\u308c\u305f\u5f37\u5316\u5b66\u7fd2\u554f\u984c\u306b\u304a\u3051\u308b\uff0c\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u63d0\u6848\u3092\u884c\u3063\u3066\u3044\u308b\uff0e\u5f93\u6765\u7814\u7a76\u3067\u306f\uff0c\u771f\u306e\u9077\u79fb\u78ba\u7387\u884c\u5217\u3092\u540c\u5b9a\u3067\u304d\u308c\u3070\u5236\u5fa1\u671f\u9593\u306e\u53ce\u76ca\u3092\u6700\u5927\u5316\u3067\u304d\u308b\u305f\u3081\uff0c\u5b66\u7fd2\u671f\u9593\u306e\u76ee\u7684\u3092\u5358\u306b\u672a\u77e5\u306e\u9077\u79fb\u78ba\u7387\u884c\u5217\u306e\u63a8\u5b9a\u3068\u3057\u3066\u3044\u308b\u304c\uff0c\u6709\u9650\u306e\u5b66\u7fd2\u671f\u9593\u306e\u3082\u3068\u3067\u306f\u63a8\u5b9a\u8aa4\u5dee\u304c\u3042\u308b\u305f\u3081\uff0c\u53ce\u76ca\u6700\u5927\u5316\u306e\u53b3\u5bc6\u306a\u4fdd\u8a3c\u306f\u306a\u3044\uff0e\u305d\u3053\u3067\u672c\u7814\u7a76\u3067\u306f\uff0c\u6709\u9650\u306e\u5b66\u7fd2\u671f\u9593\u3068\u6709\u9650\u306e\u5236\u5fa1\u671f\u9593\u306e\u5f37\u5316\u5b66\u7fd2\u554f\u984c\u306b\u304a\u3044\u3066\uff0c\u5236\u5fa1\u671f\u9593\u306e\u53ce\u76ca\u3092\u30d9\u30a4\u30ba\u57fa\u6e96\u306e\u3082\u3068\u3067\u6700\u5927\u5316\u3059\u308b\u57fa\u672c\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u63d0\u6848\u3059\u308b\uff0e\u3057\u304b\u3057\uff0c\u57fa\u672c\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u8a08\u7b97\u91cf\u304c\u6307\u6570\u30aa\u30fc\u30c0\u30fc\u306e\u305f\u3081\uff0c\u3055\u3089\u306b\u305d\u306e\u6539\u826f\u3092\u884c\u3044\uff0c\u6539\u826f\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u63d0\u6848\u3059\u308b\uff0e\u6539\u826f\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306f\u57fa\u672c\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u540c\u69d8\u306b\u53ce\u76ca\u3092\u30d9\u30a4\u30ba\u57fa\u6e96\u306e\u3082\u3068\u3067\u6700\u5927\u5316\u3059\u308b\u3053\u3068\u304c\u3067\u304d\uff0c\u304b\u3064\u305d\u306e\u8a08\u7b97\u91cf\u306f\u591a\u9805\u5f0f\u30aa\u30fc\u30c0\u30fc\u306b\u8efd\u6e1b\u3055\u308c\u3066\u3044\u308b\uff0e", "subitem_description_type": "Abstract"}, {"subitem_description": "[ENG]\nIn this paper,new algorithms are proposed based on statistical decision theory in the field of Markov decision processes under the condition that a transition probability matrix is unknown.In previous researches on RL(reinforcement learning),learning is based on only the estimation of an unknown transition probability matrix and the maximum reward is not received in a finite period,though their purpose is to maximize a reward.In our algorithms it is possible to maximize the reward within a finite period with respect to Bayes criterion.Moreover, we propose some techniques to reduce the computational complexity of our algorithm from exponential order to polynomial order", "subitem_description_type": "Abstract"}]}, "item_3_publisher_212": {"attribute_name": "\u51fa\u7248\u8005", "attribute_value_mlt": [{"subitem_publisher": "\u60c5\u5831\u51e6\u7406\u5b66\u4f1a"}]}, "item_3_relation_208": {"attribute_name": "\u8ad6\u6587ID\uff08NAID\uff09", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "110002722119", "subitem_relation_type_select": "NAID"}}]}, "item_3_select_195": {"attribute_name": "\u8457\u8005\u7248\u30d5\u30e9\u30b0", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_3_source_id_187": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1882-7764", "subitem_source_identifier_type": "ISSN"}]}, "item_3_source_id_189": {"attribute_name": "\u66f8\u8a8c\u30ec\u30b3\u30fc\u30c9ID", "attribute_value_mlt": [{"subitem_source_identifier": "AN00116647", "subitem_source_identifier_type": "NCID"}]}, "item_creator": {"attribute_name": "\u8457\u8005", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "\u524d\u7530, \u5eb7\u6210"}], "nameIdentifiers": [{"nameIdentifier": "273", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "30422033", "nameIdentifierScheme": "KAKEN - \u7814\u7a76\u8005\u691c\u7d22", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000030422033/"}]}, {"creatorNames": [{"creatorName": "\u6d6e\u7530, \u5584\u6587"}], "nameIdentifiers": [{"nameIdentifier": "90493", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u677e\u5d8b, \u654f\u6cf0"}], "nameIdentifiers": [{"nameIdentifier": "90494", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u5e73\u6fa4, \u8302\u4e00"}], "nameIdentifiers": [{"nameIdentifier": "90495", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "MAEDA, Yasunari", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "90496", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "UKITA, Yoshihumi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "90497", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "MATSUSHIMA, Toshiyasu", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "90498", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "HIRASAWA, Shigeichi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "90499", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "\u30d5\u30a1\u30a4\u30eb\u60c5\u5831", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2021-01-20"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u8ad6\u6587\u8a8c, 39(4), pp.1116-1126.pdf", "filesize": [{"value": "1.3 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1300000.0, "url": {"label": "\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u8ad6\u6587\u8a8c, 39(4), pp.1116-1126", "url": "https://kitami-it.repo.nii.ac.jp/record/8954/files/\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u8ad6\u6587\u8a8c, 39(4), pp.1116-1126.pdf"}, "version_id": "3a2e7452-3188-4193-af96-5dd34e88cf82"}]}, "item_language": {"attribute_name": "\u8a00\u8a9e", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "\u8cc7\u6e90\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "\u5b66\u7fd2\u671f\u9593\u3068\u5236\u5fa1\u671f\u9593\u306b\u5206\u5272\u3055\u308c\u305f\u5f37\u5316\u5b66\u7fd2\u554f\u984c\u306b\u304a\u3051\u308b\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u63d0\u6848", "item_titles": {"attribute_name": "\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_title": "\u5b66\u7fd2\u671f\u9593\u3068\u5236\u5fa1\u671f\u9593\u306b\u5206\u5272\u3055\u308c\u305f\u5f37\u5316\u5b66\u7fd2\u554f\u984c\u306b\u304a\u3051\u308b\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u63d0\u6848"}, {"subitem_title": "The Optimal Algorithms for the Reinforcement Learning Problem Separated into a Learning Period and a Control Period", "subitem_title_language": "en"}]}, "item_type_id": "3", "owner": "1", "path": ["1/86"], "permalink_uri": "https://kitami-it.repo.nii.ac.jp/records/8954", "pubdate": {"attribute_name": "\u516c\u958b\u65e5", "attribute_value": "2021-01-20"}, "publish_date": "2021-01-20", "publish_status": "0", "recid": "8954", "relation": {}, "relation_version_is_last": true, "title": ["\u5b66\u7fd2\u671f\u9593\u3068\u5236\u5fa1\u671f\u9593\u306b\u5206\u5272\u3055\u308c\u305f\u5f37\u5316\u5b66\u7fd2\u554f\u984c\u306b\u304a\u3051\u308b\u6700\u9069\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u63d0\u6848"], "weko_shared_id": 3}