{"id":"https://openalex.org/W3034363643","doi":"https://doi.org/10.24963/ijcai.2020/420","title":"Hybrid Learning for Multi-agent Cooperation with Sub-optimal Demonstrations","display_name":"Hybrid Learning for Multi-agent Cooperation with Sub-optimal Demonstrations","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034363643","doi":"https://doi.org/10.24963/ijcai.2020/420","mag":"3034363643"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/420","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/420","pdf_url":"https://www.ijcai.org/proceedings/2020/0420.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0420.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070755370","display_name":"Peixi Peng","orcid":"https://orcid.org/0000-0002-7427-8764"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences; Peking University","Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences; Peking University","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026303574","display_name":"Lili Cao","orcid":"https://orcid.org/0000-0002-6878-4599"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lili Cao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3037","last_page":"3043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9858999848365784,"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":0.9473999738693237,"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/computer-science","display_name":"Computer science","score":0.791100025177002},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5307348370552063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5046778917312622},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4110547602176666},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40676602721214294},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32105886936187744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791100025177002},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5307348370552063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5046778917312622},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4110547602176666},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40676602721214294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32105886936187744},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/420","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/420","pdf_url":"https://www.ijcai.org/proceedings/2020/0420.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/420","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/420","pdf_url":"https://www.ijcai.org/proceedings/2020/0420.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G2064497395","display_name":null,"funder_award_id":"61672519","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034363643.pdf","grobid_xml":"https://content.openalex.org/works/W3034363643.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1750339092","https://openalex.org/W1931877416","https://openalex.org/W1980358463","https://openalex.org/W2022504108","https://openalex.org/W2051228319","https://openalex.org/W2061562262","https://openalex.org/W2148112459","https://openalex.org/W2257979135","https://openalex.org/W2604283518","https://openalex.org/W2617547828","https://openalex.org/W2691152923","https://openalex.org/W2741122588","https://openalex.org/W2741302028","https://openalex.org/W2747213132","https://openalex.org/W2768629321","https://openalex.org/W2788862220","https://openalex.org/W2789386227","https://openalex.org/W2808602506","https://openalex.org/W2883057932","https://openalex.org/W2891663723","https://openalex.org/W2950735232","https://openalex.org/W2962957031","https://openalex.org/W2963022170","https://openalex.org/W2963277051","https://openalex.org/W2963376229","https://openalex.org/W2963809389","https://openalex.org/W2964338167","https://openalex.org/W3093287223","https://openalex.org/W3104860527","https://openalex.org/W4229812034","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4301142652","https://openalex.org/W4306290508"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"This":[0],"paper":[1,68],"aims":[2],"to":[3,24,44,100,121],"learn":[4,25,60],"multi-agent":[5,86,107],"cooperation":[6],"where":[7],"each":[8],"agent":[9],"performs":[10],"its":[11],"actions":[12,97],"in":[13,49],"a":[14,41,70,79,158],"decentralized":[15,26,74,124],"way.":[16],"In":[17],"this":[18,46,67],"case,":[19],"it":[20],"is":[21],"very":[22],"challenging":[23],"policies":[27,62],"when":[28],"the":[29,53,90,102,117,123,128,133,137,147,154,167],"rewards":[30],"are":[31,56,98,109,130,142],"global":[32],"and":[33,73,77,119,136,139],"sparse.":[34],"Recently,":[35],"learning":[36,72,82],"from":[37,63,95],"demonstrations":[38,55,129],"(LfD)":[39],"provides":[40],"promising":[42],"way":[43],"handle":[45],"challenge.":[47],"However,":[48],"many":[50,170],"practical":[51],"tasks,":[52],"available":[54],"often":[57],"sub-optimal.":[58],"To":[59],"better":[61],"these":[64],"sub-optimal":[65],"demonstrations,":[66],"follows":[69],"centralized":[71,103],"execution":[75],"framework":[76],"proposes":[78],"novel":[80],"hybrid":[81],"method":[83],"based":[84,115],"on":[85,116,157],"actor-critic.":[87],"At":[88],"first,":[89],"expert":[91],"trajectory":[92],"returns":[93],"generated":[94],"demonstration":[96],"used":[99,120],"pre-train":[101],"critic":[104,118,138],"network.":[105],"Then,":[106],"decisions":[108],"made":[110],"by":[111,132,145],"best":[112],"response":[113],"dynamics":[114],"train":[122],"actor":[125,134,140],"networks.":[126],"Finally,":[127],"updated":[131],"networks,":[135],"networks":[141],"learned":[143],"jointly":[144],"running":[146],"above":[148],"two":[149],"steps":[150],"alliteratively.":[151],"We":[152],"evaluate":[153],"proposed":[155],"approach":[156,168],"real-time":[159],"strategy":[160],"combat":[161],"game.":[162],"Experimental":[163],"results":[164],"show":[165],"that":[166],"outperforms":[169],"competing":[171],"demonstration-based":[172],"methods.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}