{"id":"https://openalex.org/W3193101426","doi":"https://doi.org/10.24963/ijcai.2021/466","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","display_name":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3193101426","doi":"https://doi.org/10.24963/ijcai.2021/466","mag":"3193101426"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/466","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/466","pdf_url":"https://www.ijcai.org/proceedings/2021/0466.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth 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/2021/0466.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035658472","display_name":"Xihuai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihuai Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062623705","display_name":"Jian Shen","orcid":"https://orcid.org/0000-0001-6099-3209"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Shen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701574","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-5701-1996"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3384","last_page":"3391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9696000218391418,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9616000056266785,"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":0.7354217767715454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706214964389801},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6849194765090942},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5671583414077759},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5196067690849304},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5167909860610962},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.501518726348877},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49970197677612305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3567906618118286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17454203963279724}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7354217767715454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706214964389801},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6849194765090942},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5671583414077759},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5196067690849304},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5167909860610962},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.501518726348877},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49970197677612305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3567906618118286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17454203963279724},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/466","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/466","pdf_url":"https://www.ijcai.org/proceedings/2021/0466.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/466","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/466","pdf_url":"https://www.ijcai.org/proceedings/2021/0466.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G129499350","display_name":"\u7f51\u7edc\u5e7f\u544a\u62cd\u5356\u7684\u535a\u5f08\u7406\u8bba\u548c\u8ba1\u7b97\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61632017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3554345598","display_name":null,"funder_award_id":"62076161","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"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3193101426.pdf","grobid_xml":"https://content.openalex.org/works/W3193101426.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W2120846115","https://openalex.org/W2475089067","https://openalex.org/W2700407638","https://openalex.org/W2785315072","https://openalex.org/W2788115019","https://openalex.org/W2798511001","https://openalex.org/W2859967432","https://openalex.org/W2904246096","https://openalex.org/W2911300280","https://openalex.org/W2913483008","https://openalex.org/W2946045694","https://openalex.org/W2950397026","https://openalex.org/W2953708620","https://openalex.org/W2962872206","https://openalex.org/W2963049774","https://openalex.org/W2972568824","https://openalex.org/W2996449210","https://openalex.org/W2997907969","https://openalex.org/W3095208105","https://openalex.org/W3106649810","https://openalex.org/W4287822810","https://openalex.org/W4288319859","https://openalex.org/W4295150809","https://openalex.org/W4295598622","https://openalex.org/W4298206671","https://openalex.org/W4299802797"],"related_works":["https://openalex.org/W2397544591","https://openalex.org/W4376639527","https://openalex.org/W1991417304","https://openalex.org/W2132876566","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W1969276875","https://openalex.org/W4310614650","https://openalex.org/W4386738330","https://openalex.org/W2788738055"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,13,18,36,40,47,89,96,124],"model-based":[4,56],"methods":[5],"in":[6,22],"multi-agent":[7,72],"reinforcement":[8],"learning":[9,49],"(MARL).":[10],"We":[11,93],"specify":[12],"dynamics":[14,78],"sample":[15,20,44,117],"complexity":[16,21,45],"and":[17,24,80,84,108],"opponent":[19,82],"MARL,":[23],"conduct":[25],"a":[26,53,77],"theoretic":[27,97],"analysis":[28],"of":[29,42,76,99],"return":[30],"discrepancy":[31],"upper":[32,37],"bound.":[33],"To":[34],"reduce":[35],"bound":[38],"with":[39,88,119],"intention":[41],"low":[43],"during":[46],"whole":[48],"process,":[50],"we":[51],"propose":[52],"novel":[54],"decentralized":[55],"MARL":[57,126],"method,":[58],"named":[59],"Adaptive":[60],"Opponent-wise":[61],"Rollout":[62],"Policy":[63],"Optimization":[64],"(AORPO).":[65],"In":[66],"AORPO,":[67],"each":[68],"agent":[69],"builds":[70],"its":[71,86],"environment":[73],"model,":[74],"consisting":[75],"model":[79],"multiple":[81],"models,":[83],"trains":[85],"policy":[87],"adaptive":[90],"opponent-wise":[91],"rollout.":[92],"further":[94],"prove":[95],"convergence":[98],"AORPO":[100,113],"under":[101],"reasonable":[102],"assumptions.":[103],"Empirical":[104],"experiments":[105],"on":[106],"competitive":[107],"cooperative":[109],"tasks":[110],"demonstrate":[111],"that":[112],"can":[114],"achieve":[115],"improved":[116],"efficiency":[118],"comparable":[120],"asymptotic":[121],"performance":[122],"over":[123],"compared":[125],"methods.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}