{"id":"https://openalex.org/W7123358153","doi":"https://doi.org/10.1109/cdc57313.2025.11312439","title":"Iteration Complexity for Robust CMDP for finite policy space","display_name":"Iteration Complexity for Robust CMDP for finite policy space","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123358153","doi":"https://doi.org/10.1109/cdc57313.2025.11312439"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th 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/A5070748487","display_name":"S. Ganguly","orcid":"https://orcid.org/0000-0002-1243-4987"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sourav Ganguly","raw_affiliation_strings":["NJIT,Dept. of Electrical and Computer Engineering,Newark,NJ,USA"],"affiliations":[{"raw_affiliation_string":"NJIT,Dept. of Electrical and Computer Engineering,Newark,NJ,USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122854425","display_name":"Arnob Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnob Ghosh","raw_affiliation_strings":["NJIT,Dept. of Electrical and Computer Engineering,Newark,NJ,USA"],"affiliations":[{"raw_affiliation_string":"NJIT,Dept. of Electrical and Computer Engineering,Newark,NJ,USA","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070748487"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85706219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2713","last_page":"2719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9222999811172485,"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":0.9222999811172485,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.013000000268220901,"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":0.010700000450015068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7544000148773193},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.4745999872684479},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4097000062465668},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.39160001277923584},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.382999986410141},{"id":"https://openalex.org/keywords/simplex","display_name":"Simplex","score":0.3797999918460846},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7544000148773193},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6467999815940857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5042999982833862},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C62438384","wikidata":"https://www.wikidata.org/wiki/Q331350","display_name":"Simplex","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35989999771118164},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.35839998722076416},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C206194317","wikidata":"https://www.wikidata.org/wiki/Q1138624","display_name":"Convex hull","level":3,"score":0.3154999911785126},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7708383798599243,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,66,88,111,135,158],"consider":[1,112,118],"the":[2,16,24,30,40,43,56,61,70,78,82,91,104,107,119,123,126,129,132,182],"robust":[3,63,108,186],"Constrained":[4],"Markov":[5],"decision":[6,127],"(RCMDP)":[7],"problem":[8,36,49,59,115,188],"of":[9,72,122],"learning":[10],"a":[11,21,35,48,113,137],"policy":[12,133],"that":[13,90,94,143,161,196],"will":[14],"maximize":[15],"cumulative":[17],"reward":[18],"while":[19],"satisfying":[20],"constraint":[22],"against":[23],"worst":[25],"possible":[26],"stochastic":[27],"model":[28],"under":[29],"unknown":[31],"uncertainty":[32],"set.":[33],"Such":[34,47],"is":[37],"relevant":[38],"when":[39],"simulated":[41],"and":[42,60,81,125,141,147,171,203],"real":[44],"environment":[45],"differ.":[46],"poses":[50],"significant":[51],"additional":[52],"challenges":[53],"compared":[54],"to":[55,68,75],"non-robust":[57,100],"CMDP":[58,101,109,187],"unconstrained":[62],"MDP":[64],"problem.":[65],"seek":[67],"characterize":[69],"number":[71],"iterations":[73],"required":[74],"bound":[76,149,173],"both":[77],"sub-optimality":[79],"gap":[80,146,170],"violations":[83],"by":[84],"at":[85],"most":[86],"\u03f5.":[87],"observe":[89],"primal-dual-based":[92],"approaches":[93],"achieves":[95],"iteration":[96],"complexity":[97],"bounds":[98,184],"for":[99,185],"cannot":[102],"achieve":[103,167,201],"same":[105],"in":[106],"case.":[110],"modified":[114],"where":[116],"we":[117],"convex":[120],"hull":[121],"policy-spaces":[124],"becomes":[128],"simplex":[130],"over":[131],"space.":[134],"propose":[136],"primal-dual":[138],"based":[139,164],"approach":[140,165,199],"show":[142,160,195],"\u03f5":[144,168],"suboptimality":[145,169],"violation":[148,172],"can":[150,166,174,200],"be":[151,175],"achieved":[152,176],"after":[153,177],"O(1/\u03f5<sup":[154,190],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155,191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>)":[156],"iterations.":[157,179],"also":[159],"an":[162],"extra-gradient":[163],"O(1/\u03f5)":[178],"This":[180],"improves":[181],"existing":[183],"OF":[189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">4</sup>).":[192],"Empirical":[193],"evaluations":[194],"our":[197],"proposed":[198],"feasible":[202],"yet":[204],"optimal":[205],"policies":[206],"very":[207],"fast.":[208]},"counts_by_year":[],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}