{"id":"https://openalex.org/W4280617966","doi":"https://doi.org/10.1137/21m1423841","title":"Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets","display_name":"Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets","publication_year":2022,"publication_date":"2022-05-19","ids":{"openalex":"https://openalex.org/W4280617966","doi":"https://doi.org/10.1137/21m1423841"},"language":"en","primary_location":{"id":"doi:10.1137/21m1423841","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1423841","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digital.lib.washington.edu/bitstreams/123d4b0a-fca2-4b75-b23c-f10b6d9bcdd8/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109433851","display_name":"Sivaramakrishnan Ramani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sivaramakrishnan Ramani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068691426","display_name":"Archis Ghate","orcid":"https://orcid.org/0000-0001-6093-5340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Archis Ghate","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3516,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81859229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"2","first_page":"989","last_page":"1017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9933000206947327,"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"}},"topics":[{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9933000206947327,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9678999781608582,"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/mathematics","display_name":"Mathematics","score":0.8183953762054443},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6181896924972534},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5610207915306091},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5176682472229004},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5031387209892273},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44557926058769226},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.42721492052078247},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4164109528064728},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4104883372783661},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39466017484664917},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1458323895931244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.13585776090621948}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.8183953762054443},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6181896924972534},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5610207915306091},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5176682472229004},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5031387209892273},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44557926058769226},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.42721492052078247},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4164109528064728},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4104883372783661},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39466017484664917},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1458323895931244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.13585776090621948},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.1137/21m1423841","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1423841","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-article"},{"id":"pmh:oai:digital.lib.washington.edu:1773/50846","is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/50846","pdf_url":"https://digital.lib.washington.edu/bitstreams/123d4b0a-fca2-4b75-b23c-f10b6d9bcdd8/download","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"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":"Thesis"}],"best_oa_location":{"id":"pmh:oai:digital.lib.washington.edu:1773/50846","is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/50846","pdf_url":"https://digital.lib.washington.edu/bitstreams/123d4b0a-fca2-4b75-b23c-f10b6d9bcdd8/download","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"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":"Thesis"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4280617966.pdf","grobid_xml":"https://content.openalex.org/works/W4280617966.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W760153864","https://openalex.org/W1484551447","https://openalex.org/W1584593412","https://openalex.org/W1965878388","https://openalex.org/W1968355947","https://openalex.org/W1971867489","https://openalex.org/W1978966474","https://openalex.org/W2006041100","https://openalex.org/W2006301680","https://openalex.org/W2032916024","https://openalex.org/W2038371077","https://openalex.org/W2059475362","https://openalex.org/W2069045459","https://openalex.org/W2092821066","https://openalex.org/W2119303899","https://openalex.org/W2125417745","https://openalex.org/W2155153696","https://openalex.org/W2165622730","https://openalex.org/W2167598103","https://openalex.org/W2168565265","https://openalex.org/W2294947825","https://openalex.org/W2469348583","https://openalex.org/W2553297237","https://openalex.org/W2623414030","https://openalex.org/W2793108066","https://openalex.org/W2887782738","https://openalex.org/W2905838893","https://openalex.org/W2963134136","https://openalex.org/W2963450292","https://openalex.org/W2969442069","https://openalex.org/W2969520023","https://openalex.org/W2989871066","https://openalex.org/W3015953475","https://openalex.org/W3018216063","https://openalex.org/W3092334672","https://openalex.org/W3123903722","https://openalex.org/W3126605566"],"related_works":["https://openalex.org/W2156021013","https://openalex.org/W2808418668","https://openalex.org/W1990452411","https://openalex.org/W2573701264","https://openalex.org/W2149476049","https://openalex.org/W1506128430","https://openalex.org/W2112369737","https://openalex.org/W91039700","https://openalex.org/W2117453943","https://openalex.org/W2123365683"],"abstract_inverted_index":{"We":[0,73],"consider":[1],"finite-":[2],"and":[3,22,217],"infinite-horizon":[4],"Markov":[5],"decision":[6],"processes":[7],"(MDPs)":[8],"with":[9,135,141,175,220],"unknown":[10],"state-transition":[11],"probabilities.":[12],"They":[13],"are":[14,117],"assumed":[15],"to":[16,18,26,85,106,119,137,207],"belong":[17],"certain":[19,59,180],"ambiguity":[20,42,98],"sets,":[21],"the":[23,28,41,62,79,86,90,94,97,103,120,138,153,157,164,167,172],"goal":[24],"is":[25,48,183],"maximize":[27],"worst-case":[29],"expected":[30],"total":[31],"discounted":[32],"reward":[33],"over":[34],"all":[35,52],"probabilities":[36],"from":[37,61,203],"these":[38,194],"sets.":[39],"Specifically,":[40],"set":[43],"for":[44,113,150,185],"any":[45],"state-action-stage":[46],"triplet":[47],"a":[49,58,127,160,176],"ball---it":[50],"includes":[51],"probability":[53],"mass":[54],"functions":[55,206],"(pmfs)":[56],"within":[57],"distance":[60,139,205],"empirical":[63],"pmf":[64],"constructed":[65],"using":[66],"historical,":[67],"independent":[68],"observations":[69],"of":[70,89,96,133,156,166],"state":[71],"transitions.":[72],"prove":[74],"that":[75,130,199,212],"optimal":[76,87,111,118,154,169],"values":[77],"in":[78,145,171],"resulting":[80],"robust":[81,110,168],"MDPs":[82],"(RMDPs)":[83],"converge":[84],"value":[88,155,165],"true":[91,121,173],"MDP":[92],"if":[93],"radii":[95],"balls":[99],"approach":[100],"zero":[101],"as":[102],"sample-size":[104],"diverges":[105],"infinity.":[107],"In":[108],"addition,":[109],"policies":[112],"sufficiently":[114],"large":[115],"sample-sizes":[116],"MDP.":[122],"These":[123],"results":[124],"rely":[125],"on":[126,163],"sufficient":[128,184],"condition":[129],"links":[131],"convergence":[132,144],"pmfs":[134],"respect":[136],"function":[140],"their":[142],"componentwise":[143],"an":[146],"appropriate":[147],"space.":[148],"Further,":[149],"finite":[151],"sample-sizes,":[152],"RMDP":[158],"provides":[159],"lower":[161],"bound":[162],"policy":[170],"MDP,":[174],"high":[177],"probability.":[178],"A":[179],"concentration":[181],"inequality":[182],"this":[186],"out-of-sample":[187,215],"performance":[188],"guarantee.":[189],"Several":[190],"well-known":[191],"distances":[192],"satisfy":[193],"conditions.":[195],"Numerical":[196],"experiments":[197],"suggest":[198],"one":[200],"can":[201],"choose":[202],"several":[204],"build":[208],"computationally":[209],"tractable":[210],"RMDPs":[211],"exhibit":[213],"good":[214],"performance,":[216],"balance":[218],"conservativeness":[219],"probabilistic":[221],"guarantees.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}