{"id":"https://openalex.org/W2569419980","doi":"https://doi.org/10.1109/cdc.2016.7798956","title":"An online primal-dual method for discounted Markov decision processes","display_name":"An online primal-dual method for discounted Markov decision processes","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2569419980","doi":"https://doi.org/10.1109/cdc.2016.7798956","mag":"2569419980"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7798956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/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":["Operation Research and Financial Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Operation Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450920","display_name":"Yichen Chen","orcid":"https://orcid.org/0000-0003-4385-4180"},"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":"Yichen Chen","raw_affiliation_strings":["Department of Computer Science, Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":1.3497,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8479746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4516","last_page":"4521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9995999932289124,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9993000030517578,"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/iterated-function","display_name":"Iterated function","score":0.6912090182304382},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6811577081680298},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6311341524124146},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6038024425506592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.589549720287323},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5590124130249023},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.48910051584243774},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.46940791606903076},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46235379576683044},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45846235752105713},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45619258284568787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32724449038505554},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.32074275612831116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24737367033958435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2157692015171051},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1929222047328949},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10184061527252197}],"concepts":[{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6912090182304382},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6811577081680298},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6311341524124146},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6038024425506592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.589549720287323},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5590124130249023},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.48910051584243774},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.46940791606903076},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46235379576683044},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45846235752105713},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45619258284568787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32724449038505554},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32074275612831116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24737367033958435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2157692015171051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1929222047328949},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10184061527252197},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2016.7798956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W29692742","https://openalex.org/W93819566","https://openalex.org/W594357522","https://openalex.org/W826457003","https://openalex.org/W1499021337","https://openalex.org/W1568229137","https://openalex.org/W1603765807","https://openalex.org/W1745373831","https://openalex.org/W1835716857","https://openalex.org/W1904705466","https://openalex.org/W1941445455","https://openalex.org/W1984901446","https://openalex.org/W1985160654","https://openalex.org/W2020677283","https://openalex.org/W2086161653","https://openalex.org/W2092851214","https://openalex.org/W2098432798","https://openalex.org/W2103446957","https://openalex.org/W2119567691","https://openalex.org/W2149464156","https://openalex.org/W2160859982","https://openalex.org/W2162664081","https://openalex.org/W2169324952","https://openalex.org/W2312609093","https://openalex.org/W2487375125","https://openalex.org/W2949510529","https://openalex.org/W3035712376","https://openalex.org/W4214717370","https://openalex.org/W4243772471","https://openalex.org/W4298023569","https://openalex.org/W6603785215","https://openalex.org/W6676641278","https://openalex.org/W6683742051"],"related_works":["https://openalex.org/W1542224353","https://openalex.org/W1661087619","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"We":[0,11,40,75],"consider":[1],"the":[2,14,48,52,58,73,82,87],"online":[3],"solution":[4],"of":[5,51],"discounted":[6],"Markov":[7],"decision":[8],"processes":[9],"(MDP).":[10],"focus":[12],"on":[13],"black-box":[15],"learning":[16],"model":[17],"where":[18],"transition":[19,23],"probabilities":[20],"and":[21,60,68],"state":[22,35,66],"cost":[24],"are":[25],"unknown.":[26],"Instead,":[27],"a":[28,42,77],"simulator":[29],"is":[30],"available":[31],"to":[32],"generate":[33],"random":[34],"transitions":[36,67],"under":[37],"given":[38],"actions.":[39],"propose":[41],"stochastic":[43],"primal-dual":[44],"algorithm":[45,56],"for":[46],"solving":[47],"linear":[49],"formulation":[50],"Bellman":[53],"equation.":[54],"The":[55],"updates":[57],"primal":[59],"dual":[61,88],"iterates":[62,89],"by":[63,72],"using":[64],"sample":[65,69],"costs":[70],"generated":[71],"simulator.":[74],"provide":[76],"thresholding":[78],"procedure":[79],"that":[80],"recovers":[81],"exact":[83],"optimal":[84],"policy":[85],"from":[86],"with":[90],"high":[91],"probability.":[92]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}