{"id":"https://openalex.org/W4314947445","doi":"https://doi.org/10.1109/cdc51059.2022.9992419","title":"Policy gradient primal-dual mirror descent for constrained MDPs with large state spaces","display_name":"Policy gradient primal-dual mirror descent for constrained MDPs with large state spaces","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4314947445","doi":"https://doi.org/10.1109/cdc51059.2022.9992419"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992419","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992419","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st 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/A5008672638","display_name":"Dong-Sheng Ding","orcid":"https://orcid.org/0000-0002-5051-4777"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongsheng Ding","raw_affiliation_strings":["University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,90089"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087790067","display_name":"Mihailo R. Jovanovi\u0107","orcid":"https://orcid.org/0000-0002-4181-2924"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihailo R. Jovanovic","raw_affiliation_strings":["University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,90089"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008672638"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19340648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4892","last_page":"4897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998000264167786,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998000264167786,"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":0.9994000196456909,"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":0.9993000030517578,"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/sublinear-function","display_name":"Sublinear function","score":0.8514994978904724},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6666345596313477},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6421574950218201},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6386215686798096},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5869570970535278},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5753764510154724},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5662490129470825},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5588080883026123},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5030762553215027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.49014076590538025},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4404716193675995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4332748353481293},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4197099804878235},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4193938970565796},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4173329472541809},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.39248350262641907},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3218408226966858},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2441590130329132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13614201545715332},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.10138306021690369},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0883370041847229},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0632147490978241}],"concepts":[{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.8514994978904724},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6666345596313477},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6421574950218201},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6386215686798096},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5869570970535278},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5753764510154724},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5662490129470825},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5588080883026123},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5030762553215027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49014076590538025},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4404716193675995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4332748353481293},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4197099804878235},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4193938970565796},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4173329472541809},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39248350262641907},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3218408226966858},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2441590130329132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13614201545715332},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.10138306021690369},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0883370041847229},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0632147490978241},{"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992419","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992419","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1992208280","https://openalex.org/W2091918879","https://openalex.org/W2615070957","https://openalex.org/W2788014517","https://openalex.org/W2991391803","https://openalex.org/W3121342653","https://openalex.org/W3125031134","https://openalex.org/W3127686539","https://openalex.org/W3171210634","https://openalex.org/W3200353301","https://openalex.org/W3210035896","https://openalex.org/W4206497039","https://openalex.org/W4214717370","https://openalex.org/W4221157223","https://openalex.org/W4287829052","https://openalex.org/W4294691315","https://openalex.org/W4315471900","https://openalex.org/W4381739798","https://openalex.org/W6737893269","https://openalex.org/W6748512255","https://openalex.org/W6751725685","https://openalex.org/W6756427573","https://openalex.org/W6767486501","https://openalex.org/W6770009701","https://openalex.org/W6771404325","https://openalex.org/W6774406872","https://openalex.org/W6774521036","https://openalex.org/W6780486084","https://openalex.org/W6780587392","https://openalex.org/W6785471904","https://openalex.org/W6789855942","https://openalex.org/W6796690604","https://openalex.org/W6796728928","https://openalex.org/W6798335325","https://openalex.org/W6798643612","https://openalex.org/W6802333366","https://openalex.org/W6803197606","https://openalex.org/W6809872370","https://openalex.org/W6810414227"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W2041416246","https://openalex.org/W3020853991","https://openalex.org/W3035836947"],"abstract_inverted_index":{"We":[0,17],"study":[1],"constrained":[2,8,116],"sequential":[3],"decision-making":[4],"problems":[5],"modeled":[6],"by":[7],"Markov":[9],"decision":[10],"processes":[11],"with":[12,61,104],"potentially":[13],"infinite":[14],"state":[15],"spaces.":[16],"propose":[18],"a":[19,62],"Bregman":[20],"distance-based":[21],"direct":[22],"policy":[23,27,37,43],"search":[24],"method":[25,39,45],"\u2013":[26,32],"gradient":[28,53,75],"primal-dual":[29,38,44],"mirror":[30],"descent":[31],"which":[33],"includes":[34],"the":[35,41,51,73,84,97,101,109,115],"natural":[36],"and":[40,69,89],"projected":[42],"as":[46],"two":[47],"special":[48],"cases.":[49],"When":[50,72],"exact":[52,74],"is":[54,76],"known,":[55],"we":[56,79],"prove":[57],"dimension-free":[58,102],"global":[59],"convergence":[60],"sublinear":[63],"rate":[64],"in":[65,83,114],"both":[66],"optimality":[67],"gap":[68],"constraint":[70],"violation.":[71],"not":[77],"available,":[78],"instantiate":[80],"our":[81],"algorithm":[82],"linear":[85],"function":[86],"approximation":[87],"setting":[88],"establish":[90],"sample":[91],"complexity":[92],"guarantees.":[93],"The":[94],"introduction":[95],"of":[96,111],"Bregman-distance":[98],"regularizers":[99],"enjoys":[100],"property":[103],"applicability":[105],"to":[106],"large-scale":[107],"spaces,":[108],"first":[110],"its":[112],"kind":[113],"RL":[117],"literature.":[118]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}