{"id":"https://openalex.org/W4405104242","doi":"https://doi.org/10.1109/milcom61039.2024.10773784","title":"Designing Near-Optimal Partially Observable Reinforcement Learning","display_name":"Designing Near-Optimal Partially Observable Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-28","ids":{"openalex":"https://openalex.org/W4405104242","doi":"https://doi.org/10.1109/milcom61039.2024.10773784"},"language":"en","primary_location":{"id":"doi:10.1109/milcom61039.2024.10773784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom61039.2024.10773784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020579600","display_name":"Ming Shi","orcid":"https://orcid.org/0000-0001-9941-9095"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ming Shi","raw_affiliation_strings":["The Ohio State University,Dept. of ECE,Columbus,OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Dept. of ECE,Columbus,OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384384","display_name":"Yingbin Liang","orcid":"https://orcid.org/0000-0003-2631-4262"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingbin Liang","raw_affiliation_strings":["The Ohio State University,Dept. of ECE,Columbus,OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Dept. of ECE,Columbus,OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035752536","display_name":"Ness B. Shroff","orcid":"https://orcid.org/0000-0002-4606-6879"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ness Shroff","raw_affiliation_strings":["The Ohio State University,Dept. of ECE and CSE,Columbus,OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Dept. of ECE and CSE,Columbus,OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020579600"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19820103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"463","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.6956999897956848,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.6956999897956848,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6901999711990356,"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/observable","display_name":"Observable","score":0.8104478120803833},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7809668779373169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.647784948348999},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4760577380657196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3464726209640503},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.143469899892807},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08894306421279907},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06554216146469116}],"concepts":[{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.8104478120803833},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7809668779373169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.647784948348999},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4760577380657196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3464726209640503},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.143469899892807},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08894306421279907},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06554216146469116},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/milcom61039.2024.10773784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom61039.2024.10773784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2032100464","https://openalex.org/W2118726574","https://openalex.org/W2139137304","https://openalex.org/W2142819538","https://openalex.org/W2142953715","https://openalex.org/W2149960632","https://openalex.org/W2959895084","https://openalex.org/W3129060066","https://openalex.org/W4297882641","https://openalex.org/W6729089391","https://openalex.org/W6736209634","https://openalex.org/W6810084060","https://openalex.org/W6839779563","https://openalex.org/W6849431214","https://openalex.org/W6849660209","https://openalex.org/W6853061584"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1994680671","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2000283393","https://openalex.org/W2920061524","https://openalex.org/W2002320543","https://openalex.org/W2061947244"],"abstract_inverted_index":{"Partially":[0],"observable":[1,106],"Markov":[2],"decision":[3],"processes":[4],"(POMDPs)":[5],"have":[6,17,129],"been":[7],"widely":[8],"applied":[9],"in":[10,21,25,33,42],"various":[11],"real-world":[12],"applications.":[13],"However,":[14],"existing":[15],"results":[16],"shown":[18],"that":[19,121,161,181],"learning":[20,108],"POMDPs":[22,160,173],"is":[23,53,81],"intractable":[24],"the":[26,34,59,63,91,102,150],"worst":[27],"case.":[28],"The":[29],"main":[30],"challenge":[31],"lies":[32],"lack":[35],"of":[36,65,152,159,172],"latent":[37],"state":[38,78,113],"information.":[39,114],"For":[40,169],"example,":[41],"wireless":[43],"channel":[44],"scheduling,":[45],"due":[46],"to":[47,61,83,94,139,184],"energy":[48],"and":[49,98,109,192],"security":[50],"constraints,":[51],"it":[52],"usually":[54],"difficult":[55],"or":[56],"impossible":[57],"for":[58,100,145],"user":[60],"know":[62],"conditions/states":[64],"all":[66],"channels.":[67],"Thus,":[68],"a":[69,118,123],"key":[70],"fundamental":[71,96],"question":[72],"here":[73],"is:":[74],"how":[75],"much":[76],"online":[77],"information":[79],"(OSI)":[80],"sufficient":[82],"achieve":[84],"tractability?":[85],"In":[86],"this":[87],"paper,":[88],"we":[89,116,128,132,155,177],"make":[90],"first":[92],"effort":[93],"establish":[95,117],"conditions":[97],"methods":[99],"bridging":[101],"gap":[103],"between":[104],"partially":[105],"reinforcement":[107],"networking":[110],"with":[111,165,174],"incomplete":[112],"Specifically,":[115],"lower":[119,193],"bound":[120],"reveals":[122],"surprising":[124],"hardness":[125],"result:":[126],"unless":[127],"full":[130],"OSI,":[131,176],"need":[133],"an":[134,141],"exponentially":[135],"scaling":[136],"sample":[137],"complexity":[138],"obtain":[140],"\u03f5-optimal":[142],"policy":[143],"solution":[144],"POMDPs.":[146],"Nonetheless,":[147],"motivated":[148],"by":[149,187],"structures":[151],"practical":[153],"systems,":[154],"identify":[156],"important":[157],"subclasses":[158,171],"are":[162,182],"tractable,":[163],"even":[164],"only":[166],"partial":[167,175],"OSI.":[168],"two":[170],"provide":[178],"new":[179,189],"algorithms":[180],"proved":[183],"be":[185],"near-optimal":[186],"establishing":[188],"regret":[190],"upper":[191],"bounds.":[194]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}