{"id":"https://openalex.org/W4406354667","doi":"https://doi.org/10.1109/tevc.2025.3529503","title":"Zeroth-Order Actor\u2013Critic: An Evolutionary Framework for Sequential Decision Problems","display_name":"Zeroth-Order Actor\u2013Critic: An Evolutionary Framework for Sequential Decision Problems","publication_year":2025,"publication_date":"2025-01-14","ids":{"openalex":"https://openalex.org/W4406354667","doi":"https://doi.org/10.1109/tevc.2025.3529503"},"language":"en","primary_location":{"id":"doi:10.1109/tevc.2025.3529503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tevc.2025.3529503","pdf_url":null,"source":{"id":"https://openalex.org/S93787993","display_name":"IEEE Transactions on Evolutionary Computation","issn_l":"1089-778X","issn":["1089-778X","1941-0026"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Evolutionary Computation","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/A5113368722","display_name":"Yuheng Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yuheng Lei","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083537762","display_name":"Yao Lyu","orcid":"https://orcid.org/0000-0003-1539-472X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Lyu","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029301375","display_name":"Guojian Zhan","orcid":"https://orcid.org/0000-0002-1246-4860"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojian Zhan","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375832","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-7192-5153"},"institutions":[{"id":"https://openalex.org/I4210113771","display_name":"Sunrise Medical (United States)","ror":"https://ror.org/01z0h5j41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113771"]},{"id":"https://openalex.org/I4210114338","display_name":"Suning (China)","ror":"https://ror.org/02hcww794","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210114338"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["SunRising AI Ltd., Beijing, China","SunRising AI Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SunRising AI Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210113771"]},{"raw_affiliation_string":"SunRising AI Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210114338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426834","display_name":"Jiangtao Li","orcid":"https://orcid.org/0000-0002-9754-0008"},"institutions":[{"id":"https://openalex.org/I4210113771","display_name":"Sunrise Medical (United States)","ror":"https://ror.org/01z0h5j41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113771"]},{"id":"https://openalex.org/I4210114338","display_name":"Suning (China)","ror":"https://ror.org/02hcww794","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210114338"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jiangtao Li","raw_affiliation_strings":["SunRising AI Ltd., Beijing, China","SunRising AI Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SunRising AI Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210113771"]},{"raw_affiliation_string":"SunRising AI Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210114338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072222039","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0003-0282-8621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036282981","display_name":"Sifa Zheng","orcid":"https://orcid.org/0000-0001-5160-1365"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifa Zheng","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5113368722"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":10.034,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97543085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"29","issue":"2","first_page":"555","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.5644999742507935,"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"}},"topics":[{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.5644999742507935,"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/evolutionary-computation","display_name":"Evolutionary computation","score":0.6260368824005127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6010167002677917},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.5906447768211365},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5303637981414795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47878706455230713},{"id":"https://openalex.org/keywords/evolutionary-programming","display_name":"Evolutionary programming","score":0.4352201819419861}],"concepts":[{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.6260368824005127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6010167002677917},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.5906447768211365},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5303637981414795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47878706455230713},{"id":"https://openalex.org/C121835503","wikidata":"https://www.wikidata.org/wiki/Q2596288","display_name":"Evolutionary programming","level":3,"score":0.4352201819419861},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tevc.2025.3529503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tevc.2025.3529503","pdf_url":null,"source":{"id":"https://openalex.org/S93787993","display_name":"IEEE Transactions on Evolutionary Computation","issn_l":"1089-778X","issn":["1089-778X","1941-0026"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Evolutionary Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G1095835165","display_name":null,"funder_award_id":"52221005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G330528761","display_name":null,"funder_award_id":"2020YFB1600200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1595159159","https://openalex.org/W1965455100","https://openalex.org/W1988115241","https://openalex.org/W2018691083","https://openalex.org/W2056877664","https://openalex.org/W2089177739","https://openalex.org/W2104578628","https://openalex.org/W2112036188","https://openalex.org/W2119717200","https://openalex.org/W2137104525","https://openalex.org/W2138507099","https://openalex.org/W2145339207","https://openalex.org/W2152195021","https://openalex.org/W2728455196","https://openalex.org/W2769471004","https://openalex.org/W2795399141","https://openalex.org/W2842089854","https://openalex.org/W2906697496","https://openalex.org/W2918933107","https://openalex.org/W2951278471","https://openalex.org/W2951841062","https://openalex.org/W2954989419","https://openalex.org/W2963157343","https://openalex.org/W2963390429","https://openalex.org/W2963900541","https://openalex.org/W2979187345","https://openalex.org/W3004384589","https://openalex.org/W3037429136","https://openalex.org/W3046992251","https://openalex.org/W3091512219","https://openalex.org/W3094704314","https://openalex.org/W3155836214","https://openalex.org/W3163478863","https://openalex.org/W3165179404","https://openalex.org/W3180708423","https://openalex.org/W3185181536","https://openalex.org/W3209552190","https://openalex.org/W3213218351","https://openalex.org/W4224216677","https://openalex.org/W4253187718","https://openalex.org/W4283382154","https://openalex.org/W4285071855","https://openalex.org/W4313068970","https://openalex.org/W4362650413","https://openalex.org/W4366158867","https://openalex.org/W4382936420","https://openalex.org/W4389297218","https://openalex.org/W4394006698","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6639086533","https://openalex.org/W6677183884","https://openalex.org/W6682262322","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6735641298","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6745515306","https://openalex.org/W6746622358","https://openalex.org/W6748839928","https://openalex.org/W6750322874","https://openalex.org/W6754787993","https://openalex.org/W6755459763","https://openalex.org/W6755903938","https://openalex.org/W6756870468","https://openalex.org/W6762760680","https://openalex.org/W6763476460","https://openalex.org/W6771587926","https://openalex.org/W6786442853","https://openalex.org/W6788186211","https://openalex.org/W6794585241","https://openalex.org/W6795803320","https://openalex.org/W6797024940","https://openalex.org/W6801951374","https://openalex.org/W6891880838"],"related_works":["https://openalex.org/W2528958959","https://openalex.org/W2091246427","https://openalex.org/W2171662586","https://openalex.org/W4285805405","https://openalex.org/W609513197","https://openalex.org/W2102580788","https://openalex.org/W2391924736","https://openalex.org/W1560122427","https://openalex.org/W2141433557","https://openalex.org/W1540041346"],"abstract_inverted_index":{"Evolutionary":[0],"algorithms":[1],"(EAs)":[2],"have":[3],"shown":[4],"promise":[5],"in":[6,26,84,106,180,226,252],"solving":[7,227],"sequential":[8],"decision":[9],"problems":[10,18],"(SDPs)":[11],"by":[12],"simplifying":[13],"them":[14],"to":[15,44,76,81,102,122,143,171],"static":[16,238],"optimization":[17,239],"and":[19,79,109,130,150,157,195,240],"searching":[20],"for":[21],"the":[22,48,112,119,125,132,164,178,221,235,242],"optimal":[23],"policy":[24,114,154,159,185],"parameters":[25,179],"a":[27,93,172,181],"zeroth-order":[28,113,158],"way.":[29],"While":[30],"these":[31,89],"methods":[32,57,73,205,247],"are":[33,74],"highly":[34],"versatile,":[35],"they":[36],"often":[37],"suffer":[38],"from":[39],"high":[40],"sample":[41,68],"complexity":[42],"due":[43],"their":[45],"ignorance":[46],"of":[47,128,134,166,188,216,224,244,254],"underlying":[49],"temporal":[50],"structures.":[51],"In":[52,137],"contrast,":[53],"reinforcement":[54],"learning":[55],"(RL)":[56],"typically":[58],"formulate":[59],"SDPs":[60,129],"as":[61,237],"Markov":[62,126],"Decision":[63],"Process":[64],"(MDP).":[65],"Although":[66],"more":[67],"efficient":[69],"than":[70],"EAs,":[71],"RL":[72,204,246],"restricted":[75],"differentiable":[77],"policies":[78,213],"prone":[80],"getting":[82],"stuck":[83],"local":[85],"optima.":[86],"To":[87,162],"address":[88],"issues,":[90],"we":[91,168],"propose":[92,101],"novel":[94],"evolutionary":[95],"framework":[96],"Zeroth-Order":[97],"Actor-Critic":[98],"(ZOAC).":[99],"We":[100,116,198],"use":[103],"step-wise":[104],"exploration":[105],"parameter":[107,147],"space":[108,148],"theoretically":[110],"derive":[111],"gradient.":[115],"further":[117],"utilize":[118],"actor-critic":[120],"architecture":[121],"effectively":[123],"leverage":[124],"property":[127],"reduce":[131],"variance":[133],"gradient":[135],"estimators.":[136],"each":[138],"iteration,":[139],"ZOAC":[140,225,229],"employs":[141],"samplers":[142],"collect":[144],"trajectories":[145],"with":[146,202,214],"exploration,":[149],"alternates":[151],"between":[152],"first-order":[153,250],"evaluation":[155],"(PEV)":[156],"improvement":[160],"(PIM).":[161],"evaluate":[163],"effectiveness":[165],"ZOAC,":[167],"apply":[169],"it":[170,201],"challenging":[173],"multi-lane":[174],"driving":[175,184],"task,":[176],"optimizing":[177,210],"rule-based,":[182],"non-differentiable":[183],"that":[186,233],"consists":[187],"three":[189,207],"sub-modules:":[190],"behavior":[191],"selection,":[192],"path":[193],"planning,":[194],"trajectory":[196],"tracking.":[197],"also":[199],"compare":[200],"gradient-based":[203,245],"on":[206],"Gymnasium":[208],"tasks,":[209],"neural":[211],"network":[212],"thousands":[215],"parameters.":[217],"Experimental":[218],"results":[219],"demonstrate":[220],"strong":[222],"capability":[223],"SDPs.":[228],"significantly":[230],"outperforms":[231],"EAs":[232],"treat":[234],"problem":[236],"matches":[241],"performance":[243],"even":[248],"without":[249],"information,":[251],"terms":[253],"total":[255],"average":[256],"return":[257],"across":[258],"all":[259],"tasks.":[260]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}