{"_buckets": {"deposit": "9803c66b-3924-465c-b8c5-9b5465b84870"}, "_deposit": {"created_by": 2, "id": "513", "owners": [2], "pid": {"revision_id": 0, "type": "depid", "value": "513"}, "status": "published"}, "_oai": {"id": "oai:fit.repo.nii.ac.jp:00000513", "sets": ["311"]}, "author_link": ["2502", "2507", "2508", "2506", "2505", "2503", "2504", "2501", "2500"], "item_3_alternative_title_23": {"attribute_name": "タイトル（ヨミ）", "attribute_value_mlt": [{"subitem_alternative_title": "カクリツ カンキョウカ デノ モデル ベース ガクシュウ"}]}, "item_3_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2011-09", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "12", "bibliographicPageStart": "9", "bibliographicVolumeNumber": "44", "bibliographic_titles": [{"bibliographic_title": "福岡工業大学研究論集"}]}]}, "item_3_description_17": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_3_description_47": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"subitem_description": "論文(Article)", "subitem_description_type": "Other"}]}, "item_3_description_5": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "Model based learning can reevaluate the utility of every state, according to a measure of urgency. Prioritized sweeping is a typical algorithm for efficient state updating. In a stochastic environment, a probability distribution can be used to represent the uncertainty of the Q-value caused by probabilistic state transitions or probabilistic rewards. The product of the confidence interval and the Bellman error is used to provide a measure for prioritizing,which takes account of the level of confidence and also yields a measure of urgency. The performance of this approach in the trap domain is examined and compared with that of the ordinary sweeping method. Experimental results indicate that the proposed approach results in a more effective exploration of the state than does the use of conventional sweeping methods.", "subitem_description_type": "Other"}]}, "item_3_full_name_2": {"attribute_name": "著者(ヨミ)", "attribute_value_mlt": [{"nameIdentifiers": [{"nameIdentifier": "2503", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "タムラ, タケシ"}]}, {"nameIdentifiers": [{"nameIdentifier": "2504", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "ツルオカ, ヒサシ"}]}, {"nameIdentifiers": [{"nameIdentifier": "2505", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "ヤマグチ, アキヒロ"}]}]}, "item_3_full_name_3": {"attribute_name": "別言語の著者", "attribute_value_mlt": [{"nameIdentifiers": [{"nameIdentifier": "2506", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "TAMURA, Takeshi"}]}, {"nameIdentifiers": [{"nameIdentifier": "2507", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "TSURUOKA, Hisashi"}]}, {"nameIdentifiers": [{"nameIdentifier": "2508", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "YAMAGUCHI, Akihiro"}]}]}, "item_3_publisher_37": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "福岡工業大学"}]}, "item_3_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "02876620", "subitem_source_identifier_type": "ISSN"}]}, "item_3_text_18": {"attribute_name": "形態", "attribute_value_mlt": [{"subitem_text_value": "855208 bytes"}]}, "item_3_text_38": {"attribute_name": "出版者（ヨミ）", "attribute_value_mlt": [{"subitem_text_value": "フクオカ コウギョウ ダイガク"}]}, "item_3_text_48": {"attribute_name": "資源タイプ・ローカル", "attribute_value_mlt": [{"subitem_text_value": "紀要論文"}]}, "item_3_text_49": {"attribute_name": "資源タイプ・NII", "attribute_value_mlt": [{"subitem_text_value": "Departmental Bulletin Paper"}]}, "item_3_text_50": {"attribute_name": "資源タイプ・DCMI", "attribute_value_mlt": [{"subitem_text_value": "text"}]}, "item_3_text_51": {"attribute_name": "資源タイプ・ローカル表示コード", "attribute_value_mlt": [{"subitem_text_value": "01"}]}, "item_3_text_77": {"attribute_name": "URI", "attribute_value_mlt": [{"subitem_text_value": "http://hdl.handle.net/11478/1289"}]}, "item_3_version_type_19": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "田村, 剛士"}], "nameIdentifiers": [{"nameIdentifier": "2500", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "鶴岡, 久"}], "nameIdentifiers": [{"nameIdentifier": "2501", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "山口, 明宏"}], "nameIdentifiers": [{"nameIdentifier": "2502", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2020-09-14"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "11478-1289_p9.pdf", "filesize": [{"value": "855.2 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 855200.0, "url": {"label": "11478-1289_p9.pdf", "url": "https://fit.repo.nii.ac.jp/record/513/files/11478-1289_p9.pdf"}, "version_id": "f7bc6cc1-845e-4745-82d4-9239210f4ef2"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "model based learning", "subitem_subject_scheme": "Other"}, {"subitem_subject": "prioritized sweeping", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Q-value", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Bellman error", "subitem_subject_scheme": "Other"}, {"subitem_subject": "confidence interval", "subitem_subject_scheme": "Other"}, {"subitem_subject": "model based learning", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "prioritized sweeping", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Q-value", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Bellman error", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "confidence interval", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "departmental bulletin paper", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "確率環境下でのモデルベース学習", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "確率環境下でのモデルベース学習"}, {"subitem_title": "Model Based Learning in Stochastic Environments", "subitem_title_language": "en"}]}, "item_type_id": "3", "owner": "2", "path": ["311"], "permalink_uri": "http://hdl.handle.net/11478/1289", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-05-28"}, "publish_date": "2019-05-28", "publish_status": "0", "recid": "513", "relation": {}, "relation_version_is_last": true, "title": ["確率環境下でのモデルベース学習"], "weko_shared_id": 2}