{"id":"https://openalex.org/W7137806946","doi":"https://doi.org/10.1609/aaai.v40i20.38767","title":"Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions","display_name":"Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137806946","doi":"https://doi.org/10.1609/aaai.v40i20.38767"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i20.38767","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38767","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i20.38767","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128133230","display_name":"Reda Ouhamma","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Reda Ouhamma","raw_affiliation_strings":["EPFL - EPF Lausanne"],"affiliations":[{"raw_affiliation_string":"EPFL - EPF Lausanne","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082009236","display_name":"Maryam Kamgarpour","orcid":"https://orcid.org/0000-0003-0230-3518"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maryam Kamgarpour","raw_affiliation_strings":["EPFL - EPF Lausanne"],"affiliations":[{"raw_affiliation_string":"EPFL - EPF Lausanne","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5128133230"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02141328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"20","first_page":"17170","last_page":"17178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8246999979019165,"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":0.8246999979019165,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.061500001698732376,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.03550000116229057,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.7095000147819519},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.5508999824523926},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5460000038146973},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5270000100135803},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5138999819755554},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4821999967098236},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.47510001063346863},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47279998660087585}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.7095000147819519},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5651999711990356},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4586000144481659},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42829999327659607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3767000138759613},{"id":"https://openalex.org/C117521176","wikidata":"https://www.wikidata.org/wiki/Q7849341","display_name":"Tsallis entropy","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C201779956","wikidata":"https://www.wikidata.org/wiki/Q5426803","display_name":"Ergodicity","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.2874999940395355},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.2653999924659729},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2621999979019165},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i20.38767","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38767","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i20.38767","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38767","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,49,105],"address":[1],"payoff-based":[2],"decentralized":[3],"learning":[4],"in":[5],"infinite-horizon":[6],"zero-sum":[7],"Markov":[8],"games.":[9],"In":[10],"this":[11,91],"setting,":[12],"each":[13],"player":[14],"makes":[15],"decisions":[16],"based":[17],"solely":[18],"on":[19,102],"received":[20],"rewards,":[21],"without":[22],"observing":[23],"the":[24,61,84,103,120,127],"opponent's":[25],"strategy":[26],"or":[27],"actions,":[28],"nor":[29],"sharing":[30],"information.":[31],"Prior":[32],"works":[33],"established":[34],"polynomial-time":[35,108],"convergence":[36,109],"to":[37,82,110],"an":[38,111],"approximate":[39,112],"Nash":[40,113],"equilibrium":[41,114],"under":[42],"strong":[43],"reachability":[44,69],"and":[45,70,122],"mixing":[46,71],"time":[47],"assumptions.":[48],"propose":[50],"a":[51,64,107],"convergent":[52],"algorithm":[53],"that":[54],"significantly":[55],"relaxes":[56],"these":[57],"assumptions,":[58],"requiring":[59],"only":[60],"existence":[62],"of":[63,119],"single":[65],"policy":[66,86,123],"with":[67],"bounded":[68],"time.":[72],"Our":[73],"key":[74],"algorithmic":[75],"novelty":[76],"is":[77],"introducing":[78],"Tsallis":[79,128],"entropy":[80,129],"regularization":[81],"smooth":[83],"best-response":[85],"updates.":[87],"By":[88],"suitably":[89],"tuning":[90],"regularization,":[92],"we":[93],"ensure":[94],"sufficient":[95],"exploration,":[96],"thus":[97],"bypassing":[98],"previous":[99],"stringent":[100],"assumptions":[101],"MDP.":[104],"prove":[106],"by":[115,126],"establishing":[116],"novel":[117],"properties":[118],"value":[121],"updates":[124],"induced":[125],"regularizer.":[130]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}