{"id":"https://openalex.org/W4375869192","doi":"https://doi.org/10.1109/icassp49357.2023.10095800","title":"Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help","display_name":"Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869192","doi":"https://doi.org/10.1109/icassp49357.2023.10095800"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095800","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"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/A5089892883","display_name":"Yunbo Qiu","orcid":"https://orcid.org/0000-0001-5069-6673"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Qiu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067942871","display_name":"Yue Jin","orcid":"https://orcid.org/0000-0002-0344-4868"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Jin","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050690756","display_name":"Lebin Yu","orcid":"https://orcid.org/0000-0003-4566-3820"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lebin Yu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370523","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-9849-7558"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441855","display_name":"Xudong Zhang","orcid":"https://orcid.org/0000-0002-6465-7437"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39381205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9668999910354614,"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"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8306680917739868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6367779970169067},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44326549768447876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34896594285964966},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33500978350639343},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14251241087913513}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8306680917739868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367779970169067},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44326549768447876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34896594285964966},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33500978350639343},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14251241087913513},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095800","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1529399279","https://openalex.org/W2617547828","https://openalex.org/W2620645529","https://openalex.org/W2803155336","https://openalex.org/W2937310911","https://openalex.org/W2963390684","https://openalex.org/W2964338167","https://openalex.org/W2978148161","https://openalex.org/W2982316857","https://openalex.org/W3037582147","https://openalex.org/W3089506933","https://openalex.org/W3128366769","https://openalex.org/W3173894685","https://openalex.org/W3208346261","https://openalex.org/W4287758406","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4320015948","https://openalex.org/W6631533588","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6749304979","https://openalex.org/W6751139674","https://openalex.org/W6768731700","https://openalex.org/W6779101081","https://openalex.org/W6780070463","https://openalex.org/W6790614080","https://openalex.org/W6793862206","https://openalex.org/W6803595505"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"has":[4],"achieved":[5],"great":[6],"progress":[7],"in":[8,11,15,84,130],"cooperative":[9,48],"tasks":[10],"recent":[12],"years.":[13],"However,":[14],"the":[16,35,106,125],"local":[17,22],"reward":[18],"scheme,":[19],"where":[20],"only":[21],"rewards":[23,31],"for":[24,101,114],"each":[25,82,102],"agent":[26],"are":[27,58,109],"given":[28],"without":[29],"global":[30],"shared":[32],"by":[33],"all":[34],"agents,":[36],"traditional":[37],"MARL":[38,75,128],"algorithms":[39],"lack":[40],"sufficient":[41],"consideration":[42],"of":[43,127],"agents\u2019":[44,50,99],"mutual":[45,51],"influence.":[46],"In":[47,66],"tasks,":[49],"influence":[52],"is":[53],"especially":[54],"important":[55],"since":[56],"agents":[57,79,113],"supposed":[59],"to":[60,62,77,80,86,95,111],"coordinate":[61],"achieve":[63],"better":[64],"performance.":[65],"this":[67],"paper,":[68],"we":[69],"propose":[70],"a":[71],"novel":[72],"algorithm":[73],"Mutual-Help-based":[74],"(MH-MARL)":[76],"instruct":[78],"help":[81],"other":[83,98,112],"order":[85],"promote":[87],"cooperation.":[88],"MH-MARL":[89,123],"utilizes":[90],"an":[91],"expected":[92,97,107],"action":[93],"module":[94],"generate":[96],"actions":[100,108],"particular":[103],"agent.":[104],"Then,":[105],"delivered":[110],"selective":[115],"imitation":[116],"during":[117],"training.":[118],"Experimental":[119],"results":[120],"show":[121],"that":[122],"improves":[124],"performance":[126],"both":[129],"success":[131],"rate":[132],"and":[133],"cumulative":[134],"reward.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}