{"id":"https://openalex.org/W4386932574","doi":"https://doi.org/10.1007/978-3-031-44223-0_6","title":"Latent-Conditioned Policy Gradient for\u00a0Multi-Objective Deep Reinforcement Learning","display_name":"Latent-Conditioned Policy Gradient for\u00a0Multi-Objective Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386932574","doi":"https://doi.org/10.1007/978-3-031-44223-0_6"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-44223-0_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-44223-0_6","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102812354","display_name":"Takuya Kanazawa","orcid":"https://orcid.org/0000-0002-1499-374X"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya Kanazawa","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd., Kokubunji, Tokyo, 185-8601, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd., Kokubunji, Tokyo, 185-8601, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103731588","display_name":"Chetan Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I86725329","display_name":"Hitachi Global Storage Technologies (United States)","ror":"https://ror.org/02q0s1x22","country_code":"US","type":"company","lineage":["https://openalex.org/I86725329"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chetan Gupta","raw_affiliation_strings":["Industrial AI Lab, Hitachi America, Ltd.\u00a0R &D, Santa Clara, CA, 95054, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial AI Lab, Hitachi America, Ltd.\u00a0R &D, Santa Clara, CA, 95054, USA","institution_ids":["https://openalex.org/I86725329"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102812354"],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.0217,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88412378,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9990000128746033,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9858999848365784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8449923992156982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8326249718666077},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6676980257034302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5928332805633545},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.5903680324554443},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5601152181625366},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5120568871498108},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.48004114627838135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46657857298851013},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.442484974861145},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4383618235588074},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.2932313084602356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09481269121170044}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8449923992156982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8326249718666077},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6676980257034302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5928332805633545},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.5903680324554443},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5601152181625366},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5120568871498108},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.48004114627838135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46657857298851013},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.442484974861145},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4383618235588074},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.2932313084602356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09481269121170044},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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":[{"id":"doi:10.1007/978-3-031-44223-0_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-44223-0_6","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1518318201","https://openalex.org/W1543572792","https://openalex.org/W1987725948","https://openalex.org/W1988210060","https://openalex.org/W2012612381","https://openalex.org/W2045276965","https://openalex.org/W2058192020","https://openalex.org/W2060846151","https://openalex.org/W2098907614","https://openalex.org/W2102660061","https://openalex.org/W2106334424","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2535247013","https://openalex.org/W2625286567","https://openalex.org/W3004325772","https://openalex.org/W3021613070","https://openalex.org/W4287266177","https://openalex.org/W4312246863","https://openalex.org/W4386932574"],"related_works":["https://openalex.org/W2073298047","https://openalex.org/W1963790170","https://openalex.org/W2586328217","https://openalex.org/W2033790662","https://openalex.org/W2049264236","https://openalex.org/W317165722","https://openalex.org/W312725187","https://openalex.org/W2728870795","https://openalex.org/W4378499136","https://openalex.org/W2078568741"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}