{"id":"https://openalex.org/W4385767435","doi":"https://doi.org/10.24963/ijcai.2023/37","title":"Exploration via Joint Policy Diversity for Sparse-Reward Multi-Agent Tasks","display_name":"Exploration via Joint Policy Diversity for Sparse-Reward Multi-Agent Tasks","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767435","doi":"https://doi.org/10.24963/ijcai.2023/37"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/37","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/37","pdf_url":"https://www.ijcai.org/proceedings/2023/0037.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0037.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101814011","display_name":"Pei Xu","orcid":"https://orcid.org/0000-0003-1766-5634"},"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Xu","raw_affiliation_strings":["CRISE, Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012644","display_name":"Junge Zhang","orcid":"https://orcid.org/0000-0002-9970-394X"},"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":"Junge Zhang","raw_affiliation_strings":["CRISE, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028693655","display_name":"Kaiqi Huang","orcid":"https://orcid.org/0000-0002-2677-9273"},"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/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiqi Huang","raw_affiliation_strings":["CAS, Center for Excellence in Brain Science and Intelligence Technology","CRISE, Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS, Center for Excellence in Brain Science and Intelligence Technology","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.979,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80519294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9930999875068665,"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":0.9657999873161316,"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/computer-science","display_name":"Computer science","score":0.717641294002533},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.647250771522522},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5863586068153381},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.554309070110321},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5211912989616394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5181964039802551},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.497726708650589},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4876824617385864},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4628874957561493},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4584041237831116},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42180532217025757},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33216190338134766},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11913484334945679},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11855697631835938},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10296165943145752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717641294002533},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.647250771522522},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5863586068153381},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.554309070110321},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5211912989616394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181964039802551},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.497726708650589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4876824617385864},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4628874957561493},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4584041237831116},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42180532217025757},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33216190338134766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11913484334945679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11855697631835938},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10296165943145752},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/37","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/37","pdf_url":"https://www.ijcai.org/proceedings/2023/0037.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/37","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/37","pdf_url":"https://www.ijcai.org/proceedings/2023/0037.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767435.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1988526405","https://openalex.org/W2054314161","https://openalex.org/W2885550588","https://openalex.org/W2902298341","https://openalex.org/W2963049774","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2964067469","https://openalex.org/W2996549507","https://openalex.org/W2997502221","https://openalex.org/W3008003828","https://openalex.org/W3090684275","https://openalex.org/W3133093447","https://openalex.org/W3170473100","https://openalex.org/W3170511602","https://openalex.org/W3177652717","https://openalex.org/W3211360571","https://openalex.org/W4205779441","https://openalex.org/W4283032009","https://openalex.org/W4287867830","https://openalex.org/W4288091739","https://openalex.org/W4288594419","https://openalex.org/W4294183581","https://openalex.org/W4295598622","https://openalex.org/W4299802797"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W2625725254","https://openalex.org/W2364477340"],"abstract_inverted_index":{"Exploration":[0],"under":[1,167],"sparse":[2],"rewards":[3],"is":[4,157],"a":[5,61,79,98],"key":[6],"challenge":[7],"for":[8],"multi-agent":[9],"reinforcement":[10],"learning":[11],"problems.":[12],"Previous":[13],"works":[14],"argue":[15],"that":[16,54,115],"complex":[17],"dynamics":[18],"between":[19,87],"agents":[20,40,70],"and":[21,91,95,132],"the":[22,30,85,105,110,116,121,125,128,138,144,158,168],"huge":[23],"exploration":[24,35,68,100],"space":[25],"in":[26,46,124],"MARL":[27],"scenarios":[28],"amplify":[29],"vulnerability":[31],"of":[32,140],"classical":[33,62],"count-based":[34,63],"methods":[36,123],"when":[37,69],"combined":[38],"with":[39],"parameterized":[41,72],"by":[42,73],"neural":[43,74],"networks,":[44],"resulting":[45],"inefficient":[47],"exploration.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,77,113],"show":[53,114],"introducing":[55],"constrained":[56],"joint":[57,80,89,93,106],"policy":[58,81,90,107],"diversity":[59,82],"into":[60],"method":[64,118,156],"can":[65],"significantly":[66,119],"improve":[67],"are":[71],"networks.":[75],"Specifically,":[76],"propose":[78],"to":[83,102,152,160],"measure":[84],"difference":[86],"current":[88],"previous":[92],"policies,":[94],"then":[96],"use":[97],"filtering-based":[99],"constraint":[101],"further":[103],"refine":[104],"diversity.":[108],"Under":[109],"sparse-reward":[111,169],"setting,":[112],"proposed":[117],"outperforms":[120],"state-of-the-art":[122],"multiple-particle":[126],"environment,":[127],"Google":[129],"Research":[130],"Football,":[131],"StarCraft":[133],"II":[134],"micromanagement":[135],"tasks.":[136],"To":[137],"best":[139],"our":[141,155],"knowledge,":[142],"on":[143],"hard":[145],"3s_vs_5z":[146],"task":[147],"which":[148],"needs":[149],"non-trivial":[150],"strategies":[151,163],"defeat":[153],"enemies,":[154],"first":[159],"learn":[161],"winning":[162],"without":[164],"domain":[165],"knowledge":[166],"setting.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}