{"id":"https://openalex.org/W3019905104","doi":"https://doi.org/10.1109/tac.2020.2989702","title":"Stochastic Approximation for Risk-Aware Markov Decision Processes","display_name":"Stochastic Approximation for Risk-Aware Markov Decision Processes","publication_year":2020,"publication_date":"2020-04-22","ids":{"openalex":"https://openalex.org/W3019905104","doi":"https://doi.org/10.1109/tac.2020.2989702","mag":"3019905104"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2020.2989702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.2989702","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","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/A5070019149","display_name":"Wenjie Huang","orcid":"https://orcid.org/0000-0002-1358-213X"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjie Huang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data and Institute for Data and Decision Analytics, The Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data and Institute for Data and Decision Analytics, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019863108","display_name":"William B. Haskell","orcid":"https://orcid.org/0000-0002-9518-4310"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William B. Haskell","raw_affiliation_strings":["Krannert School of Management at Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Krannert School of Management at Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070019149"],"corresponding_institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":1.857,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86381858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"66","issue":"3","first_page":"1314","last_page":"1320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9998999834060669,"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":0.9998999834060669,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9896000027656555,"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/markov-decision-process","display_name":"Markov decision process","score":0.5501124858856201},{"id":"https://openalex.org/keywords/saddle-point","display_name":"Saddle point","score":0.5331420302391052},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5278126001358032},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5203872919082642},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.494464635848999},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4886620342731476},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48562493920326233},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.479853093624115},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4202396273612976},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4165509343147278},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.4115736484527588},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3884141147136688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3663395643234253},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3617480397224426},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.32664239406585693},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14343616366386414}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5501124858856201},{"id":"https://openalex.org/C2681867","wikidata":"https://www.wikidata.org/wiki/Q690935","display_name":"Saddle point","level":2,"score":0.5331420302391052},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5278126001358032},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5203872919082642},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.494464635848999},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4886620342731476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48562493920326233},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.479853093624115},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4202396273612976},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4165509343147278},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.4115736484527588},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3884141147136688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3663395643234253},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3617480397224426},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.32664239406585693},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14343616366386414},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2020.2989702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.2989702","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.75}],"awards":[{"id":"https://openalex.org/G89762911","display_name":null,"funder_award_id":"MOE2015-T2-2-148","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W29692742","https://openalex.org/W51049863","https://openalex.org/W1499021337","https://openalex.org/W1557270667","https://openalex.org/W1557517019","https://openalex.org/W1587828677","https://openalex.org/W1775297201","https://openalex.org/W1976406849","https://openalex.org/W1992208280","https://openalex.org/W2001009060","https://openalex.org/W2027106436","https://openalex.org/W2045843884","https://openalex.org/W2048052425","https://openalex.org/W2049968883","https://openalex.org/W2054321814","https://openalex.org/W2071983464","https://openalex.org/W2076337359","https://openalex.org/W2083231020","https://openalex.org/W2107431923","https://openalex.org/W2109122936","https://openalex.org/W2109427113","https://openalex.org/W2115211925","https://openalex.org/W2118686230","https://openalex.org/W2128347943","https://openalex.org/W2134802631","https://openalex.org/W2139914196","https://openalex.org/W2142865798","https://openalex.org/W2155581291","https://openalex.org/W2155968351","https://openalex.org/W2160769068","https://openalex.org/W2165131254","https://openalex.org/W2167696704","https://openalex.org/W2169206416","https://openalex.org/W2344944957","https://openalex.org/W2462780152","https://openalex.org/W2746553466","https://openalex.org/W2798579099","https://openalex.org/W2949963197","https://openalex.org/W2963082979","https://openalex.org/W3009585715","https://openalex.org/W3104184956","https://openalex.org/W3125893104","https://openalex.org/W3162902207","https://openalex.org/W4205326910","https://openalex.org/W4213065535","https://openalex.org/W4233696721","https://openalex.org/W4243772471","https://openalex.org/W4249513058","https://openalex.org/W6601225455","https://openalex.org/W6677067356","https://openalex.org/W6684763656","https://openalex.org/W6687063787","https://openalex.org/W6704438963"],"related_works":["https://openalex.org/W3094031457","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532","https://openalex.org/W1907128005","https://openalex.org/W2514909387","https://openalex.org/W29692742","https://openalex.org/W2120339885","https://openalex.org/W4246247437","https://openalex.org/W2032229253"],"abstract_inverted_index":{"We":[0],"develop":[1],"a":[2,28],"stochastic":[3,29],"approximation-type":[4],"algorithm":[5,16,72,100],"to":[6,38],"solve":[7],"finite":[8],"state/action,":[9],"infinite-horizon,":[10],"risk-aware":[11,42],"Markov":[12],"decision":[13],"processes.":[14],"Our":[15],"has":[17],"two":[18],"loops.":[19],"The":[20,32],"inner":[21],"loop":[22,34],"computes":[23],"the":[24,67,71,94],"risk":[25,47],"by":[26,60],"solving":[27],"saddle-point":[30],"problem.":[31],"outer":[33],"performs":[35],"Q-":[36],"learning":[37,88],"compute":[39],"an":[40,76],"optimal":[41,83],"policy.":[43],"Several":[44],"widely":[45],"investigated":[46],"measures":[48],"(e.g.,":[49],"conditional":[50],"value-at-risk,":[51],"optimized":[52],"certainty":[53],"equivalent,":[54],"and":[55,66,87],"absolute":[56],"semideviation)":[57],"are":[58,73],"covered":[59],"our":[61,99],"algorithm.":[62],"Almost":[63],"sure":[64],"convergence":[65,68,96],"rate":[69,89,97],"of":[70,98],"established.":[74],"For":[75],"error":[77],"tolerance":[78],"\u03b5":[79],">":[80],"0":[81],"for":[82],"Q-value":[84],"estimation":[85],"gap":[86],"k":[90],"\u2208":[91],"(1/2,":[92],"1],":[93],"overall":[95],"is":[101],"\u03a9((ln(1/\u03b4\u03b5)/\u03b5":[102],"<sup":[103,107,112],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[104,108,113],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[105],")":[106,115],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1/k</sup>":[109],"+":[110],"(ln(1/\u03b5))":[111],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1/(1-k)</sup>":[114],"with":[116],"probability":[117],"at":[118],"least":[119],"1":[120],"-":[121],"\u03b4.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}