{"id":"https://openalex.org/W3096763169","doi":"https://doi.org/10.1007/978-3-030-61616-8_30","title":"Improving Multi-agent Reinforcement Learning with Imperfect Human Knowledge","display_name":"Improving Multi-agent Reinforcement Learning with Imperfect Human Knowledge","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3096763169","doi":"https://doi.org/10.1007/978-3-030-61616-8_30","mag":"3096763169"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-61616-8_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-61616-8_30","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":"conference-paper","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/A5101172866","display_name":"Xiaoxu Han","orcid":"https://orcid.org/0009-0001-7991-5881"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxu Han","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176048","display_name":"Hongyao Tang","orcid":"https://orcid.org/0000-0001-7478-7684"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyao Tang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390903","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0002-8479-3049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["Academy of Military Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017668787","display_name":"Guang Kou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guang Kou","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047785406","display_name":"Leilei Liu","orcid":"https://orcid.org/0000-0001-5584-5746"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leilei Liu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9807999730110168,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9801999926567078,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8918380737304688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8478386402130127},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.698244035243988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6481688618659973},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4809217154979706},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.46928203105926514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46253326535224915},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4332888722419739},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42930904030799866}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8918380737304688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478386402130127},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.698244035243988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6481688618659973},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4809217154979706},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.46928203105926514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46253326535224915},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4332888722419739},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42930904030799866},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-61616-8_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-61616-8_30","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2434014514","https://openalex.org/W2774982397","https://openalex.org/W2788862220","https://openalex.org/W2794643322","https://openalex.org/W2807741983","https://openalex.org/W2902391430","https://openalex.org/W2944746440","https://openalex.org/W2963376229","https://openalex.org/W2964407556","https://openalex.org/W2966476822","https://openalex.org/W3105335800","https://openalex.org/W6603707631"],"related_works":["https://openalex.org/W2768698792","https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W1986508893","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}