{"id":"https://openalex.org/W7220975798","doi":"https://doi.org/10.48550/arxiv.2610.10326","title":"Average-Reward Reinforcement Learning for Multichain MDPs: A Hierarchical Decomposition Approach","display_name":"Average-Reward Reinforcement Learning for Multichain MDPs: A Hierarchical Decomposition Approach","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220975798","doi":"https://doi.org/10.48550/arxiv.2610.10326"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.10326","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.10326","pdf_url":"https://arxiv.org/pdf/2610.10326","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.10326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014937312","display_name":"Huizhen Yu","orcid":"https://orcid.org/0000-0002-3673-0094","observed_orcids":["https://orcid.org/0000-0002-3673-0094"]},"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":"Yu, Huizhen","raw_affiliation_strings":["Department of Computing Science University of Alberta , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta , Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157959922","display_name":"Isaiah Heidt","orcid":null,"observed_orcids":[]},"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":"Heidt, Isaiah","raw_affiliation_strings":["Department of Computing Science University of Alberta , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta , Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"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/average-reward-reinforcement-learning","display_name":"average-reward reinforcement learning","score":0.9549999833106995},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.718999981880188},{"id":"https://openalex.org/keywords/optimal-gain","display_name":"optimal gain","score":0.6069999933242798},{"id":"https://openalex.org/keywords/transient-states","display_name":"transient states","score":0.6169999837875366},{"id":"https://openalex.org/keywords/almost-sure-convergence","display_name":"almost sure convergence","score":0.8080000281333923}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6960999965667725},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6194999814033508},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5539000034332275},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5454999804496765},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3244999945163727},{"id":"https://openalex.org/C86941820","wikidata":"https://www.wikidata.org/wiki/Q6865391","display_name":"Minimisation (clinical trials)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.26179999113082886}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.10326","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.10326","pdf_url":"https://arxiv.org/pdf/2610.10326","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.10326","doi":"https://doi.org/10.48550/arxiv.2610.10326","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.10326","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.10326","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.10326","pdf_url":"https://arxiv.org/pdf/2610.10326","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5290545508","display_name":null,"funder_award_id":"RGPIN-2024-04939","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320314212","display_name":"Alberta Machine Intelligence Institute","ror":"https://ror.org/03msd8560"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220975798.pdf","grobid_xml":"https://content.openalex.org/works/W7220975798.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4402706509","https://openalex.org/W4403364548","https://openalex.org/W4403586047","https://openalex.org/W7092205832","https://openalex.org/W7111386121"],"related_works":["https://openalex.org/W7131129311","https://openalex.org/W4415181763","https://openalex.org/W2175190893","https://openalex.org/W2002035237","https://openalex.org/W4415025669","https://openalex.org/W4382619379","https://openalex.org/W7128474288","https://openalex.org/W2159692787","https://openalex.org/W2766806202","https://openalex.org/W4399756375"],"abstract_inverted_index":{"We":[0,35,85,147],"study":[1],"learning":[2,32],"optimal":[3,14,93,133],"policies":[4,98],"in":[5],"average-reward":[6,140,185],"multichain":[7,116,141,190],"Markov":[8],"decision":[9,76],"processes":[10],"(MDPs),":[11],"where":[12],"the":[13,19,48,59,74,88,92,115,132,144,163,173,181],"gain":[15,94],"may":[16],"depend":[17],"on":[18,103],"initial":[20],"state":[21,60],"and":[22,52,65,95,125,136,156],"recurrence":[23],"structures":[24],"vary":[25],"across":[26],"policies,":[27,124],"creating":[28],"challenges":[29],"for":[30,152,188],"reinforcement":[31],"(RL)":[33],"methods.":[34],"propose":[36],"an":[37,138],"asynchronous":[38],"value-iteration-based":[39],"RL":[40,186],"algorithm":[41,83,89],"that":[42,87,162],"requires":[43],"no":[44],"model":[45],"knowledge":[46],"beyond":[47],"MDP's":[49],"transition":[50],"graph":[51],"leverages":[53],"Bather's":[54],"decomposition":[55,69],"to":[56,91,120,172,194],"hierarchically":[57],"partition":[58],"space":[61],"into":[62,78],"communicating":[63],"subsystems":[64],"transient":[66,169],"states.":[67],"This":[68],"induces":[70],"a":[71],"recasting":[72],"of":[73],"global":[75],"problem":[77],"structured":[79],"subproblems,":[80],"which":[81],"our":[82,177],"exploits.":[84],"show":[86],"converges":[90],"produces":[96],"gain-optimal":[97,123],"after":[99],"finite":[100],"time.":[101],"Building":[102],"this":[104],"base":[105,145,174],"algorithm,":[106],"we":[107],"develop":[108],"two":[109,165],"further":[110],"algorithms:":[111],"one":[112],"approximately":[113],"solves":[114],"average":[117],"optimality":[118],"equations":[119],"obtain":[121],"near":[122,128],"another":[126],"targets":[127],"bias-optimality":[129],"by":[130],"approximating":[131],"bias":[134],"function":[135],"solving":[137],"induced":[139],"MDP":[142],"using":[143],"algorithm.":[146,175],"provide":[148],"almost-sure":[149],"convergence":[150],"guarantees":[151],"all":[153],"three":[154],"algorithms":[155,187],"empirically":[157],"compare":[158],"their":[159],"tradeoffs,":[160],"showing":[161],"latter":[164],"also":[166],"consistently":[167],"improve":[168],"performance":[170],"relative":[171],"To":[176],"knowledge,":[178],"these":[179],"are":[180],"first":[182],"essentially":[183],"model-free":[184],"general":[189],"MDPs":[191],"without":[192],"reductions":[193],"discounted":[195],"problems.":[196]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}