{"id":"https://openalex.org/W3114647763","doi":"https://doi.org/10.1109/itsc45102.2020.9294300","title":"Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic","display_name":"Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic","publication_year":2020,"publication_date":"2020-09-20","ids":{"openalex":"https://openalex.org/W3114647763","doi":"https://doi.org/10.1109/itsc45102.2020.9294300","mag":"3114647763"},"language":"en","primary_location":{"id":"doi:10.1109/itsc45102.2020.9294300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","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/A5007325049","display_name":"Yangang Ren","orcid":"https://orcid.org/0000-0002-1173-7230"},"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":true,"raw_author_name":"Yangang Ren","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576"},"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":"Jingliang Duan","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, 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":["State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082794136","display_name":"Yang Guan","orcid":"https://orcid.org/0000-0003-0689-0510"},"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":"Yang Guan","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101697324","display_name":"Qi Sun","orcid":"https://orcid.org/0000-0002-2664-2509"},"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":"Qi Sun","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007325049"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.121,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.90010522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9950000047683716,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8309043645858765},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.8245201706886292},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.762312650680542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7066459059715271},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6084684133529663},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.601258397102356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5248872637748718},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5189158916473389},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.4901624619960785},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46496301889419556},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43703800439834595},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.43046531081199646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3474813401699066},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.170576810836792},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1648184359073639}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8309043645858765},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.8245201706886292},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.762312650680542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7066459059715271},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6084684133529663},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.601258397102356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248872637748718},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5189158916473389},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.4901624619960785},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46496301889419556},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43703800439834595},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.43046531081199646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474813401699066},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.170576810836792},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1648184359073639},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc45102.2020.9294300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1945616565","https://openalex.org/W2105078254","https://openalex.org/W2167696704","https://openalex.org/W2257979135","https://openalex.org/W2529477964","https://openalex.org/W2602963933","https://openalex.org/W2773525213","https://openalex.org/W2773691349","https://openalex.org/W2781726626","https://openalex.org/W2896408693","https://openalex.org/W2898436992","https://openalex.org/W2916826721","https://openalex.org/W2949963197","https://openalex.org/W2963207607","https://openalex.org/W2963403593","https://openalex.org/W2964108292","https://openalex.org/W2967292964","https://openalex.org/W3002044607","https://openalex.org/W3015082424","https://openalex.org/W3101442004","https://openalex.org/W4297824641","https://openalex.org/W6640425456","https://openalex.org/W6728252718","https://openalex.org/W6735677848","https://openalex.org/W6747027214","https://openalex.org/W6747473740","https://openalex.org/W6756103505","https://openalex.org/W6759370769","https://openalex.org/W6775294054"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W4320018150","https://openalex.org/W4283320637","https://openalex.org/W4239582170","https://openalex.org/W2918664383","https://openalex.org/W106056076","https://openalex.org/W4320855730","https://openalex.org/W2135200719"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"achieved":[4],"remarkable":[5],"performance":[6],"in":[7,110,175],"numerous":[8],"sequential":[9],"decision":[10],"making":[11],"and":[12,31,75,86,152,170],"control":[13],"tasks.":[14],"However,":[15],"a":[16,131,148,153],"common":[17],"problem":[18],"is":[19],"that":[20,180],"learned":[21],"nearly":[22],"optimal":[23,101],"policy":[24,102,114,121,151,174],"always":[25],"overfits":[26],"to":[27,36,51,78,99,123,129,193],"the":[28,45,58,72,80,88,104,112,119,140,162,172,186,190],"training":[29],"environment":[30,48],"may":[32],"not":[33],"be":[34,57],"extended":[35],"situations":[37],"never":[38],"encountered":[39],"during":[40],"training.":[41],"For":[42],"practical":[43],"applications,":[44],"randomness":[46],"of":[47,60,83,142,165,189],"usually":[49],"leads":[50],"some":[52],"devastating":[53],"events,":[54],"which":[55,111,136],"should":[56],"focus":[59],"safety-critical":[61],"systems":[62],"such":[63],"as":[64],"autonomous":[65,166],"driving.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,137],"introduce":[71],"minimax":[73],"formulation":[74,97],"distributional":[76],"framework":[77,127],"improve":[79,185],"generalization":[81,187],"ability":[82,188],"RL":[84],"algorithms":[85],"develop":[87],"Minimax":[89,96],"Distributional":[90,126],"Soft":[91],"Actor-Critic":[92],"(Minimax":[93],"DSAC)":[94],"algorithm.":[95],"aims":[98,128],"seek":[100],"considering":[103],"most":[105],"severe":[106],"variations":[107],"from":[108,135],"environment,":[109],"protagonist":[113,150,191],"maximizes":[115],"action-value":[116],"function":[117],"while":[118],"adversary":[120],"tries":[122],"minimize":[124],"it.":[125],"learn":[130],"state-action":[132],"return":[133],"distribution,":[134],"can":[138,183],"model":[139],"risk":[141],"different":[143,194],"returns":[144],"explicitly,":[145],"thereby":[146],"formulating":[147],"risk-averse":[149],"risk-seeking":[154],"adversarial":[155],"policy.":[156],"We":[157],"implement":[158],"our":[159,181],"method":[160,182],"on":[161],"decision-making":[163],"tasks":[164],"vehicles":[167],"at":[168],"intersections":[169],"test":[171],"trained":[173],"distinct":[176],"environments.":[177],"Results":[178],"demonstrate":[179],"greatly":[184],"agent":[192],"environmental":[195],"variations.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}