{"id":"https://openalex.org/W2946045694","doi":"https://doi.org/10.24963/ijcai.2019/85","title":"A Regularized Opponent Model with Maximum Entropy Objective","display_name":"A Regularized Opponent Model with Maximum Entropy Objective","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2946045694","doi":"https://doi.org/10.24963/ijcai.2019/85","mag":"2946045694"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/85","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/85","pdf_url":"https://www.ijcai.org/proceedings/2019/0085.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth 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/2019/0085.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zheng Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Tian","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647484","display_name":"Ying Wen","orcid":"https://orcid.org/0000-0002-6354-1168"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ying Wen","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052384585","display_name":"Zhichen Gong","orcid":"https://orcid.org/0000-0002-2558-6314"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhichen Gong","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025763919","display_name":"Faiz Punakkath","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Faiz Punakkath","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077144356","display_name":"Shihao Zou","orcid":"https://orcid.org/0000-0002-9042-6069"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shihao Zou","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384727","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-4021-4228"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9841,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.81517331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"602","last_page":"608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9902999997138977,"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":0.9740999937057495,"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":0.6811234951019287},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6513093709945679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6013075709342957},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5058226585388184},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.49617108702659607},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4881954789161682},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48230409622192383},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.47678259015083313},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.45944228768348694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40728092193603516},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35092324018478394},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32502931356430054}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6811234951019287},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6513093709945679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6013075709342957},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5058226585388184},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.49617108702659607},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4881954789161682},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48230409622192383},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.47678259015083313},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.45944228768348694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40728092193603516},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35092324018478394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32502931356430054},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2019/85","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/85","pdf_url":"https://www.ijcai.org/proceedings/2019/0085.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10091833","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10091833/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Kraus, S, (ed.) Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19). (pp. pp. 602-608). International Joint Conferences on Artifical Intelligence (IJCAI): Macao, China. (2019)","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/85","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/85","pdf_url":"https://www.ijcai.org/proceedings/2019/0085.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2946045694.pdf","grobid_xml":"https://content.openalex.org/works/W2946045694.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W1512681781","https://openalex.org/W1786529921","https://openalex.org/W2026659355","https://openalex.org/W2085366587","https://openalex.org/W2098284983","https://openalex.org/W2098774185","https://openalex.org/W2104602264","https://openalex.org/W2107464055","https://openalex.org/W2123157758","https://openalex.org/W2142044314","https://openalex.org/W2145060720","https://openalex.org/W2475089067","https://openalex.org/W2606433045","https://openalex.org/W2609650878","https://openalex.org/W2617547828","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2798511001","https://openalex.org/W2799151646","https://openalex.org/W2897928687","https://openalex.org/W2949561945","https://openalex.org/W2950397026","https://openalex.org/W2951507724","https://openalex.org/W2963267001","https://openalex.org/W2963390138","https://openalex.org/W2963403593","https://openalex.org/W2963864421","https://openalex.org/W2964164283","https://openalex.org/W2964251366","https://openalex.org/W3005581722","https://openalex.org/W4239125046","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4394651706"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3103325625","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W1486898455","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474"],"abstract_inverted_index":{"In":[0,27],"a":[1,17,51,78,107],"single-agent":[2],"setting,":[3],"reinforcement":[4,43],"learning":[5,44],"(RL)":[6],"tasks":[7],"can":[8,88,149],"be":[9],"cast":[10],"into":[11],"an":[12,126],"inference":[13],"problem":[14],"by":[15,124],"introducing":[16],"binary":[18,33],"random":[19,34],"variable":[20,35],"o,":[21],"which":[22],"stands":[23],"for":[24],"the":[25,32,56,60,90,118,136],"\"optimality\".":[26],"this":[28],"paper,":[29],"we":[30,76,104],"redefine":[31],"o":[36],"in":[37,98],"multi-agent":[38,42],"setting":[39],"and":[40,62,84,96,141,145],"formalize":[41],"(MARL)":[45],"as":[46,65],"probabilistic":[47],"inference.":[48],"We":[49,116,130],"derive":[50],"variational":[52],"lower":[53],"bound":[54],"of":[55,58,92,114],"likelihood":[57],"achieving":[59],"optimality":[61],"name":[63],"it":[64,87],"Regularized":[66],"Opponent":[67],"Model":[68],"with":[69,112],"Maximum":[70],"Entropy":[71],"Objective":[72],"(ROMMEO).":[73],"From":[74],"ROMMEO,":[75,103],"present":[77],"novel":[79],"perspective":[80],"on":[81,135],"opponent":[82],"modeling":[83],"show":[85,146],"how":[86],"improve":[89],"performance":[91],"training":[93],"agents":[94],"theoretically":[95],"empirically":[97],"cooperative":[99],"games.":[100],"To":[101],"optimize":[102],"first":[105],"introduce":[106],"tabular":[108],"Q-iteration":[109],"method":[110],"ROMMEO-Q":[111],"proof":[113],"convergence.":[115],"extend":[117],"exact":[119],"algorithm":[120],"to":[121],"complex":[122],"environments":[123],"proposing":[125],"approximate":[127],"version,":[128],"ROMMEO-AC.":[129],"evaluate":[131],"these":[132],"two":[133],"algorithms":[134],"challenging":[137],"iterated":[138],"matrix":[139],"game":[140,143],"differential":[142],"respectively":[144],"that":[147],"they":[148],"outperform":[150],"strong":[151],"MARL":[152],"baselines.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}