乐胖代购免代理版

{"id":"https://openalex.org/W4392950152","doi":"https://doi.org/10.20965/jaciii.2024.p0380","title":"Inverse Reinforcement Learning with Agents\u2019 Biased Exploration Based on Sub-Optimal Sequential Action Data","display_name":"Inverse Reinforcement Learning with Agents\u2019 Biased Exploration Based on Sub-Optimal Sequential Action Data","publication_year":2024,"publication_date":"2024-03-19","ids":{"openalex":"https://openalex.org/W4392950152","doi":"https://doi.org/10.20965/jaciii.2024.p0380"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2024.p0380","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.20965/jaciii.2024.p0380","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037814625","display_name":"Fumito Uwano","orcid":"https://orcid.org/0000-0003-4139-2605"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumito Uwano","raw_affiliation_strings":["Faculty of Environmental, Life, Natural Science and Technology, Okayama University, 3-1-1 Tsushima-naka, Kita-ku, Okayama 700-8530, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Environmental, Life, Natural Science and Technology, Okayama University, 3-1-1 Tsushima-naka, Kita-ku, Okayama 700-8530, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101103927","display_name":"Hasegawa Satoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151549","display_name":"Konica Minolta (Japan)","ror":"https://ror.org/05dtvab05","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210151549"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Hasegawa","raw_affiliation_strings":["Konica Minolta, Inc., 2-7-2 Marunouchi, Chiyoda-ku, Tokyo 100-0005, Japan"],"affiliations":[{"raw_affiliation_string":"Konica Minolta, Inc., 2-7-2 Marunouchi, Chiyoda-ku, Tokyo 100-0005, Japan","institution_ids":["https://openalex.org/I4210151549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084452161","display_name":"Keiki Takadama","orcid":"https://orcid.org/0009-0007-0916-5505"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiki Takadama","raw_affiliation_strings":["Graduate School of Informatics and Engineering, The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu-shi, Tokyo 182-8585, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu-shi, Tokyo 182-8585, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":0,"currency":"USD","value_usd":0,"provenance":"doaj"},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":"28","issue":"2","first_page":"380","last_page":"392"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9761,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9546,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80776024},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7672833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5843921},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.55491567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5252195},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.51161796},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.41372696},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36667633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.102119386},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2024.p0380","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2024.p0380","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science","award_id":"JP21K17807"}],"datasets":[],"versions":[],"referenced_works_count":9,"referenced_works":["https://openalex.org/W1527702126","https://openalex.org/W1557517019","https://openalex.org/W2145339207","https://openalex.org/W2156163138","https://openalex.org/W2188721763","https://openalex.org/W2402734324","https://openalex.org/W2889990052","https://openalex.org/W2963523627","https://openalex.org/W3037606473"],"related_works":["https://openalex.org/W4380318855","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W3155039083","https://openalex.org/W3049728571","https://openalex.org/W2586732548","https://openalex.org/W2331917905","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2024136090"],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2],"(IRL)":[3],"estimates":[4],"a":[5],"reward":[6],"function":[7],"for":[8,51],"an":[9],"agent":[10],"to":[11,39,54,70],"behave":[12],"along":[13],"with":[14,65],"expert":[15,23,57,67,88],"data,":[16,42],"e.g.,":[17],"as":[18],"human":[19],"operation":[20],"data.":[21,59],"However,":[22],"data":[24,69,89],"usually":[25],"have":[26],"redundant":[27],"parts,":[28],"which":[29],"decrease":[30],"the":[31,37,72,75,83,92,96],"agent\u2019s":[32],"performance.":[33],"This":[34,60],"study":[35,61],"extends":[36],"IRL":[38],"sub-optimal":[40,66],"action":[41,58,68],"including":[43],"lack":[44],"and":[45,95],"detour.":[46],"The":[47,78],"proposed":[48,76,84,97],"method":[49,85],"searches":[50],"new":[52],"actions":[53],"determine":[55],"optimal":[56,87],"adopted":[62],"maze":[63],"problems":[64],"investigate":[71],"performance":[73],"of":[74],"method.":[77],"experimental":[79],"results":[80],"show":[81],"that":[82],"finds":[86],"better":[90,101],"than":[91,102],"conventional":[93],"method,":[94],"search":[98],"mechanisms":[99],"perform":[100],"random":[103],"search.":[104]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4392950152","counts_by_year":[],"updated_date":"2024-12-09T23:38:36.440911","created_date":"2024-03-20"}