{"id":"https://openalex.org/W7202204005","doi":"https://doi.org/10.1137/25m1791585","title":"Policy Optimization over General State and Action Spaces","display_name":"Policy Optimization over General State and Action Spaces","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7202204005","doi":"https://doi.org/10.1137/25m1791585"},"language":"en","primary_location":{"id":"doi:10.1137/25m1791585","is_oa":false,"landing_page_url":"https://doi.org/10.1137/25m1791585","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-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/A5044731263","display_name":"Caleb Ju","orcid":"https://orcid.org/0000-0002-9532-9030"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caleb Ju","raw_affiliation_strings":["H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA"],"raw_orcid":"https://orcid.org/0000-0002-9532-9030","affiliations":[{"raw_affiliation_string":"H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042544900","display_name":"Guanghui Lan","orcid":"https://orcid.org/0000-0002-2103-087X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanghui Lan","raw_affiliation_strings":["H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91631884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"3","first_page":"1731","last_page":"1772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8733999729156494,"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":0.8733999729156494,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.07349999994039536,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.007799999788403511,"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":0.7161999940872192},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5687999725341797},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.550000011920929},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5188000202178955},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4918000102043152},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4754999876022339},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4041999876499176}],"concepts":[{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.7161999940872192},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6399000287055969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5954999923706055},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5687999725341797},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4754999876022339},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37540000677108765},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C5871375","wikidata":"https://www.wikidata.org/wiki/Q1780715","display_name":"Compact convergence","level":4,"score":0.36500000953674316},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C48216909","wikidata":"https://www.wikidata.org/wiki/Q6889156","display_name":"Modes of convergence (annotated index)","level":5,"score":0.2849999964237213},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C64980692","wikidata":"https://www.wikidata.org/wiki/Q16191959","display_name":"Symbolic convergence theory","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C116149140","wikidata":"https://www.wikidata.org/wiki/Q2070951","display_name":"Descent direction","level":4,"score":0.2549000084400177},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/25m1791585","is_oa":false,"landing_page_url":"https://doi.org/10.1137/25m1791585","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6574599742889404,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1638471481","display_name":"2021 BUDGET REQUEST FOR THE DOE COMPUTATIONAL SCIENCE GRADUATE FELLOWSHIP (CSGF) GRANT","funder_award_id":"DESC0022158","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8152494097","display_name":null,"funder_award_id":"FA9550-22-1-0447","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1983874169","https://openalex.org/W2021468336","https://openalex.org/W2074680702","https://openalex.org/W2087617385","https://openalex.org/W2091565802","https://openalex.org/W2145339207","https://openalex.org/W2169713291","https://openalex.org/W2334782222","https://openalex.org/W2616761010","https://openalex.org/W2735095024","https://openalex.org/W2766447205","https://openalex.org/W2902907165","https://openalex.org/W2948432982","https://openalex.org/W2963534244","https://openalex.org/W2998050631","https://openalex.org/W3025638325","https://openalex.org/W3047197922","https://openalex.org/W3127686539","https://openalex.org/W3217314940","https://openalex.org/W4226246290","https://openalex.org/W4252698487","https://openalex.org/W4381739798","https://openalex.org/W4386291772","https://openalex.org/W4386863830","https://openalex.org/W4401142486","https://openalex.org/W4405190532","https://openalex.org/W4406195240","https://openalex.org/W4411467213"],"related_works":[],"abstract_inverted_index":{"Abstract.":[0],"Reinforcement":[1],"learning":[2],"(RL)":[3],"problems":[4,142,173],"over":[5],"general":[6,70,170],"state":[7,71,171],"and":[8,26,72,158,215],"action":[9,73],"spaces":[10],"are":[11],"notoriously":[12],"challenging.":[13],"In":[14,50],"contrast":[15],"to":[16,67,79,92,124,130,136,169,199],"the":[17,24,30,37,60,163,181,186,203,209,212],"tableau":[18],"setting,":[19],"one":[20],"cannot":[21],"enumerate":[22],"all":[23],"states":[25],"then":[27,148],"iteratively":[28],"update":[29],"policies":[31],"for":[32,108,132,155],"each":[33],"state.":[34],"This":[35],"prevents":[36],"application":[38],"of":[39,59,140,152,165,183,188,211],"many":[40],"well-studied":[41],"RL":[42,141,172,223],"methods,":[43],"especially":[44],"those":[45],"with":[46,69,174,221],"provable":[47],"convergence":[48,122,129,164,196],"guarantees.":[49],"this":[51,84],"paper,":[52],"we":[53,88,100],"first":[54],"present":[55,101],"a":[56,102,120],"substantial":[57],"generalization":[58],"recently":[61],"developed":[62],"policy":[63,95,104,145,156],"mirror":[64],"descent":[65],"method":[66,85,107],"deal":[68],"spaces.":[74,179],"We":[75,118,147],"introduce":[76],"new":[77,201],"approaches":[78],"incorporate":[80],"function":[81,112],"approximation":[82,113,153],"into":[83],"so":[86],"that":[87],"do":[89],"not":[90],"need":[91],"use":[93],"explicit":[94],"parameterization":[96],"at":[97],"all.":[98],"Moreover,":[99],"novel":[103],"dual":[105],"averaging":[106],"which":[109],"possibly":[110],"simpler":[111],"techniques":[114],"can":[115,218],"be":[116,200,219],"applied.":[117],"establish":[119],"linear":[121],"rate":[123],"global":[125],"optimality":[126],"or":[127,177],"sublinear":[128],"stationarity":[131],"these":[133,166,189],"methods":[134,167,214],"applied":[135,168],"solve":[137],"different":[138],"classes":[139],"under":[143],"exact":[144],"evaluation.":[146],"define":[149],"proper":[150],"notions":[151],"errors":[154],"evaluation":[157],"investigate":[159],"their":[160,195],"impact":[161],"on":[162],"either":[175],"finite-action":[176],"continuous-action":[178],"To":[180],"best":[182],"our":[184],"knowledge,":[185],"development":[187],"algorithmic":[190],"frameworks":[191],"as":[192,194],"well":[193],"analysis":[197],"appear":[198],"in":[202],"literature.":[204],"Preliminary":[205],"numerical":[206],"results":[207],"demonstrate":[208],"robustness":[210],"aforementioned":[213],"show":[216],"they":[217],"competitive":[220],"state-of-the-art":[222],"algorithms.":[224]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-08-12T00:00:00"}