{"id":"https://openalex.org/W2783797945","doi":"https://doi.org/10.1109/cdc.2017.8264388","title":"Risk-aware Q-learning for Markov decision processes","display_name":"Risk-aware Q-learning for Markov decision processes","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783797945","doi":"https://doi.org/10.1109/cdc.2017.8264388","mag":"2783797945"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2017.8264388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","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/A5070019149","display_name":"Wenjie Huang","orcid":"https://orcid.org/0000-0002-1358-213X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Wenjie Huang","raw_affiliation_strings":["Department of Industrial Systems Engineering & Management, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Systems Engineering & Management, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"William B. Haskell","raw_affiliation_strings":["Department of Industrial Systems Engineering & Management, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Systems Engineering & Management, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070019149"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":3.8749,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9372417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.9993000030517578,"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":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9753999710083008,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.9649999737739563,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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/markov-decision-process","display_name":"Markov decision process","score":0.8414061665534973},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.7845314741134644},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7699340581893921},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6276952028274536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.583381175994873},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5324365496635437},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5194865465164185},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5172039270401001},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5037145018577576},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4822691082954407},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4319555163383484},{"id":"https://openalex.org/keywords/finite-state","display_name":"Finite state","score":0.4162876605987549},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3339557647705078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3222087323665619},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27302777767181396}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8414061665534973},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7845314741134644},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7699340581893921},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6276952028274536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.583381175994873},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5324365496635437},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5194865465164185},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5172039270401001},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5037145018577576},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4822691082954407},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4319555163383484},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.4162876605987549},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3339557647705078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3222087323665619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27302777767181396},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2017.8264388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W580164506","https://openalex.org/W1541527977","https://openalex.org/W1587828677","https://openalex.org/W1601081659","https://openalex.org/W1647779468","https://openalex.org/W1953426937","https://openalex.org/W1971867489","https://openalex.org/W1976406849","https://openalex.org/W2001009060","https://openalex.org/W2009398741","https://openalex.org/W2019291268","https://openalex.org/W2027106436","https://openalex.org/W2066503680","https://openalex.org/W2076337359","https://openalex.org/W2107431923","https://openalex.org/W2109122936","https://openalex.org/W2109427113","https://openalex.org/W2128422927","https://openalex.org/W2134802631","https://openalex.org/W2136013738","https://openalex.org/W2139914196","https://openalex.org/W2146502635","https://openalex.org/W2147750403","https://openalex.org/W2155581291","https://openalex.org/W2169206416","https://openalex.org/W2170419304","https://openalex.org/W2487144912","https://openalex.org/W2798579099","https://openalex.org/W2963590277","https://openalex.org/W3104184956","https://openalex.org/W3125145310","https://openalex.org/W3125893104","https://openalex.org/W4233696721","https://openalex.org/W4243772471","https://openalex.org/W4247165901","https://openalex.org/W6617021176","https://openalex.org/W6678911804","https://openalex.org/W6681435938","https://openalex.org/W6820564557"],"related_works":["https://openalex.org/W1970303738","https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W1050019105","https://openalex.org/W2107384771","https://openalex.org/W2970347269"],"abstract_inverted_index":{"We":[0,56],"are":[1],"interested":[2],"in":[3],"developing":[4],"reinforcement":[5],"learning":[6],"algorithm":[7,33,62],"to":[8,78],"tackle":[9],"risk-aware":[10,71],"sequential":[11],"decision":[12,24],"making":[13],"problems.":[14],"The":[15],"model":[16],"we":[17,46,75],"investigate":[18],"is":[19,34],"a":[20,38],"discounted":[21],"infinite-horizon":[22],"Markov":[23],"processes":[25],"with":[26,42,67],"finite":[27],"state":[28],"and":[29,45],"action":[30],"spaces.":[31],"Our":[32],"based":[35],"on":[36],"estimating":[37],"general":[39],"minimax":[40],"function":[41],"stochastic":[43,65],"approximation,":[44],"show":[47],"that":[48],"several":[49,79],"risk":[50,82],"measures":[51],"fall":[52],"within":[53],"this":[54,61],"form.":[55],"derive":[57],"finite-time":[58],"bounds":[59],"for":[60],"by":[63],"combining":[64],"approximation":[66],"the":[68],"theories":[69],"of":[70,81],"dynamic":[72],"programming.":[73],"Finally,":[74],"present":[76],"extensions":[77],"variations":[80],"measures.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}