{"id":"https://openalex.org/W4399768462","doi":"https://doi.org/10.1109/tit.2024.3416202","title":"Efficient Reinforcement Learning With Impaired Observability: Learning to Act With Delayed and Missing State Observations","display_name":"Efficient Reinforcement Learning With Impaired Observability: Learning to Act With Delayed and Missing State Observations","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399768462","doi":"https://doi.org/10.1109/tit.2024.3416202"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2024.3416202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2024.3416202","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-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/A5103116351","display_name":"Minshuo Chen","orcid":"https://orcid.org/0009-0004-9924-7843"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minshuo Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0009-0004-9924-7843","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109734458","display_name":"Jie Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Meng","raw_affiliation_strings":["Department of Management Science and Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0009-0004-0279-5393","affiliations":[{"raw_affiliation_string":"Department of Management Science and Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659384","display_name":"Yu Bai","orcid":"https://orcid.org/0009-0009-0524-2264"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Bai","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041526408","display_name":"Yinyu Ye","orcid":"https://orcid.org/0009-0001-3239-2622"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinyu Ye","raw_affiliation_strings":["Department of Management Science and Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Management Science and Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042307561","display_name":"H. Vincent Poor","orcid":"https://orcid.org/0000-0002-2062-131X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Vincent Poor","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-2062-131X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100707460","display_name":"Mengdi Wang","orcid":"https://orcid.org/0000-0002-2101-9507"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengdi Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-2101-9507","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61918189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"70","issue":"10","first_page":"7251","last_page":"7272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9925000071525574,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.9246109127998352},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6906576752662659},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5378780364990234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5309020280838013},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5116589665412903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45835840702056885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2910804748535156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28426820039749146},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19817233085632324},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.14241337776184082}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9246109127998352},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6906576752662659},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5378780364990234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5309020280838013},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5116589665412903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45835840702056885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2910804748535156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28426820039749146},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19817233085632324},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.14241337776184082}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2024.3416202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2024.3416202","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G3250582783","display_name":null,"funder_award_id":"IIS-2107304","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G3668962789","display_name":null,"funder_award_id":"DMS-1953686","funder_id":"https://openalex.org/F4320337380","funder_display_name":"Division of Mathematical Sciences"},{"id":"https://openalex.org/G5429545050","display_name":null,"funder_award_id":"1006977","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7869195739","display_name":null,"funder_award_id":"ECCS- 2335876","funder_id":"https://openalex.org/F4320337392","funder_display_name":"Division of Electrical, Communications and Cyber Systems"}],"funders":[{"id":"https://openalex.org/F4320319788","display_name":"C3.ai Digital Transformation Institute","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W21934178","https://openalex.org/W1974730074","https://openalex.org/W1977185509","https://openalex.org/W2008136256","https://openalex.org/W2009432182","https://openalex.org/W2032100464","https://openalex.org/W2034725503","https://openalex.org/W2071780137","https://openalex.org/W2097951814","https://openalex.org/W2098432798","https://openalex.org/W2117864026","https://openalex.org/W2118980425","https://openalex.org/W2146332392","https://openalex.org/W2161966552","https://openalex.org/W2489939061","https://openalex.org/W2730527299","https://openalex.org/W2904087713","https://openalex.org/W3020125231","https://openalex.org/W3035658936","https://openalex.org/W3040890460","https://openalex.org/W3170657538","https://openalex.org/W3173185086","https://openalex.org/W4206530644","https://openalex.org/W4211030719","https://openalex.org/W4214717370","https://openalex.org/W4239466562","https://openalex.org/W4283641403","https://openalex.org/W4285428701","https://openalex.org/W4298187497","https://openalex.org/W4308245294","https://openalex.org/W4319166803","https://openalex.org/W4319452227","https://openalex.org/W4376639574","https://openalex.org/W6600849757","https://openalex.org/W6639039794","https://openalex.org/W6639926649","https://openalex.org/W6662929504","https://openalex.org/W6677741321","https://openalex.org/W6681472862","https://openalex.org/W6682884278","https://openalex.org/W6683603353","https://openalex.org/W6683841709","https://openalex.org/W6736209634","https://openalex.org/W6741268893","https://openalex.org/W6746523204","https://openalex.org/W6752725515","https://openalex.org/W6756464082","https://openalex.org/W6757991398","https://openalex.org/W6774050812","https://openalex.org/W6776510272","https://openalex.org/W6779700097","https://openalex.org/W6780070372","https://openalex.org/W6784748513","https://openalex.org/W6796668474","https://openalex.org/W6839097925","https://openalex.org/W6839779563","https://openalex.org/W6839928121","https://openalex.org/W6840875318","https://openalex.org/W6843717944","https://openalex.org/W6844010370","https://openalex.org/W6845955164","https://openalex.org/W6846551069","https://openalex.org/W6849431214","https://openalex.org/W6849489661","https://openalex.org/W6849886849"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990","https://openalex.org/W2615757685"],"abstract_inverted_index":{"In":[0],"real-world":[1],"reinforcement":[2],"learning":[3,142],"(RL)":[4],"systems,":[5],"various":[6],"forms":[7],"of":[8,28,78,109,124,155,164,167],"impaired":[9,127,172],"observability":[10,128],"can":[11],"complicate":[12],"matters.":[13],"These":[14],"situations":[15],"arise":[16],"when":[17],"an":[18],"agent":[19,39],"is":[20,115,121],"unable":[21],"to":[22,32,132,176,188],"observe":[23],"the":[24,29,38,79,96,107,116,122,133,146,152,156,165,168,177],"most":[25],"recent":[26],"state":[27,65,110],"system":[30],"due":[31],"latency":[33],"or":[34],"lossy":[35],"channels,":[36],"yet":[37],"must":[40,59],"still":[41],"make":[42],"real-time":[43],"decisions.":[44],"This":[45],"paper":[46],"introduces":[47],"a":[48,162],"theoretical":[49],"investigation":[50],"into":[51],"efficient":[52],"RL":[53,94],"in":[54,95],"control":[55],"systems":[56],"where":[57],"agents":[58],"act":[60],"with":[61,145,181],"delayed":[62,97],"and":[63,70,75,98,104,111,119,136],"missing":[64,99],"observations.":[66],"We":[67],"present":[68],"algorithms":[69],"establish":[71],"near-optimal":[72],"regret":[73,147],"upper":[74],"lower":[76],"bounds,":[77],"form":[80],"<inline-formula":[81],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[83],"<tex-math":[84],"notation=\"LaTeX\">$\\tilde":[85],"{\\mathcal":[86],"{O}}(\\sqrt":[87],"{{\\mathrm":[88],"{":[89],"poly}}(H)":[90],"SAK})$":[91],"</tex-math></inline-formula>,":[92],"for":[93],"observation":[100],"settings.":[101],"Here":[102],"S":[103],"A":[105],"are":[106,186],"sizes":[108],"action":[112],"spaces,":[113],"H":[114],"time":[117],"horizon":[118],"K":[120],"number":[123],"episodes.":[125],"Despite":[126],"posing":[129],"significant":[130],"challenges":[131],"policy":[134,170],"class":[135],"planning,":[137],"our":[138,190],"results":[139,185],"demonstrate":[140],"that":[141],"remains":[143],"efficient,":[144],"bound":[148],"optimally":[149],"depending":[150],"on":[151],"state-action":[153],"size":[154],"original":[157],"system.":[158],"Additionally,":[159],"we":[160],"provide":[161],"characterization":[163],"performance":[166],"optimal":[169,178],"under":[171],"observability,":[173],"comparing":[174],"it":[175],"value":[179],"obtained":[180],"full":[182],"observability.":[183],"Numerical":[184],"provided":[187],"support":[189],"theory.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}