{"id":"https://openalex.org/W3012223798","doi":"https://doi.org/10.1109/cdc40024.2019.9029743","title":"Stochastic Primal-Dual Method for Learning Mixture Policies in Markov Decision Processes","display_name":"Stochastic Primal-Dual Method for Learning Mixture Policies in Markov Decision Processes","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3012223798","doi":"https://doi.org/10.1109/cdc40024.2019.9029743","mag":"3012223798"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th 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/A5039622279","display_name":"Masoud Badiei Khuzani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155590","display_name":"Management Sciences (United States)","ror":"https://ror.org/05shz5j84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155590"]},{"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":true,"raw_author_name":"Masoud Badiei Khuzani","raw_affiliation_strings":["Department of Management Sciences, Stanford University"],"affiliations":[{"raw_affiliation_string":"Department of Management Sciences, Stanford University","institution_ids":["https://openalex.org/I4210155590","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027136767","display_name":"Varun Vasudevan","orcid":"https://orcid.org/0000-0001-5013-6836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varun Vasudevan","raw_affiliation_strings":["Institute for Computational and Mathematical Engineering (ICME), Stanford University"],"affiliations":[{"raw_affiliation_string":"Institute for Computational and Mathematical Engineering (ICME), Stanford University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062327519","display_name":"Hongyi Ren","orcid":"https://orcid.org/0000-0001-6999-0370"},"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"]},{"id":"https://openalex.org/I4210155590","display_name":"Management Sciences (United States)","ror":"https://ror.org/05shz5j84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyi Ren","raw_affiliation_strings":["Department of Management Sciences, Stanford University"],"affiliations":[{"raw_affiliation_string":"Department of Management Sciences, Stanford University","institution_ids":["https://openalex.org/I4210155590","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381484","display_name":"Lei Xing","orcid":"https://orcid.org/0000-0003-2536-5359"},"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"]},{"id":"https://openalex.org/I4210155590","display_name":"Management Sciences (United States)","ror":"https://ror.org/05shz5j84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Xing","raw_affiliation_strings":["Department of Management Sciences, Stanford University"],"affiliations":[{"raw_affiliation_string":"Department of Management Sciences, Stanford University","institution_ids":["https://openalex.org/I4210155590","https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039622279"],"corresponding_institution_ids":["https://openalex.org/I4210155590","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20741731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"1293","last_page":"1300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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":0.9966999888420105,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9950000047683716,"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/markov-decision-process","display_name":"Markov decision process","score":0.834678053855896},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6731353998184204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4945339858531952},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4783487021923065},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.46793124079704285},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4589146375656128},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.4529217779636383},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44904083013534546},{"id":"https://openalex.org/keywords/stochastic-programming","display_name":"Stochastic programming","score":0.4412316381931305},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.42592981457710266},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4259246587753296},{"id":"https://openalex.org/keywords/convex-hull","display_name":"Convex hull","score":0.4207269549369812},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4198969602584839},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.24908530712127686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19079983234405518}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.834678053855896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6731353998184204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4945339858531952},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4783487021923065},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.46793124079704285},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4589146375656128},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4529217779636383},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44904083013534546},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.4412316381931305},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.42592981457710266},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4259246587753296},{"id":"https://openalex.org/C206194317","wikidata":"https://www.wikidata.org/wiki/Q1138624","display_name":"Convex hull","level":3,"score":0.4207269549369812},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4198969602584839},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.24908530712127686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19079983234405518},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1520045492","https://openalex.org/W1745373831","https://openalex.org/W1963529497","https://openalex.org/W1964535365","https://openalex.org/W2016384870","https://openalex.org/W2022416612","https://openalex.org/W2098432798","https://openalex.org/W2169324952","https://openalex.org/W2788943438","https://openalex.org/W2921683795","https://openalex.org/W4206742934","https://openalex.org/W6631271631","https://openalex.org/W6748763001"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W2156021013","https://openalex.org/W4399157305","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"We":[0,23,97],"investigate":[1],"the":[2,25,51,62,65,70,82,87,94,110,116,119,124,139,154],"problem":[3,71],"of":[4,21,27,54,57,64,90,118,126],"learning":[5],"efficient":[6],"policy":[7,29,37,47],"for":[8,79],"an":[9,73],"infinite-horizon,":[10],"discounted":[11],"cost,":[12],"Markov":[13],"decision":[14],"process":[15],"(MDP)":[16],"with":[17,105],"a":[18,28,36,40,44,55,100],"large":[19],"number":[20,125],"states.":[22],"compute":[24],"actions":[26],"that":[30,138],"is":[31],"nearly":[32],"as":[33,35,72],"good":[34],"chosen":[38],"by":[39,50],"suitable":[41],"oracle":[42],"from":[43],"given":[45],"mixture":[46,66],"class":[48],"characterized":[49,111],"convex":[52],"hull":[53],"set":[56],"base":[58,91],"policies.":[59],"To":[60],"learn":[61],"coefficients":[63],"model,":[67],"we":[68,114],"recast":[69],"approximate":[74],"linear":[75],"programming":[76],"(ALP)":[77],"formulation":[78],"MDPs,":[80],"where":[81],"feature":[83],"vectors":[84],"correspond":[85],"to":[86,108,129,153],"occupation":[88],"measures":[89],"policies":[92],"on":[93],"state-action":[95],"space.":[96],"then":[98],"propose":[99],"projection-free":[101],"stochastic":[102,121],"primal-dual":[103,141],"method":[104],"Bregman":[106],"divergence":[107],"solve":[109],"ALP.":[112],"Furthermore,":[113],"analyze":[115],"efficiency":[117,145],"proposed":[120,140],"algorithm,":[122],"namely":[123],"rounds":[127],"required":[128],"achieve":[130],"near":[131],"optimal":[132],"objective":[133],"value.":[134],"Numerical":[135],"results":[136],"show":[137],"algorithm":[142],"achieves":[143],"better":[144],"and":[146],"lower":[147],"variance":[148],"across":[149],"different":[150],"trials":[151],"compared":[152],"penalty":[155],"function":[156],"method.":[157]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}