{"id":"https://openalex.org/W4385767956","doi":"https://doi.org/10.24963/ijcai.2023/784","title":"Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning (Extended Abstract)","display_name":"Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning (Extended Abstract)","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767956","doi":"https://doi.org/10.24963/ijcai.2023/784"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/784","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/784","pdf_url":"https://www.ijcai.org/proceedings/2023/0784.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0784.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027912723","display_name":"Xiaoteng Ma","orcid":"https://orcid.org/0000-0002-7250-6268"},"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":"Xiaoteng Ma","raw_affiliation_strings":["Tsinghua University","Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104089865","display_name":"Shuai Ma","orcid":"https://orcid.org/0000-0002-2904-6796"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Ma","raw_affiliation_strings":["Sun Yat-Sen University","School of Business, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]},{"raw_affiliation_string":"School of Business, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904019","display_name":"Xia Li","orcid":"https://orcid.org/0000-0003-1651-8528"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xia","raw_affiliation_strings":["Sun Yat-Sen University","School of Business, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]},{"raw_affiliation_string":"School of Business, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014109600","display_name":"Qianchuan Zhao","orcid":"https://orcid.org/0000-0002-7952-5621"},"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":"Qianchuan Zhao","raw_affiliation_strings":["Tsinghua University","Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6925","last_page":"6930"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9793999791145325,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9710000157356262,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semivariance","display_name":"Semivariance","score":0.9771876335144043},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8572647571563721},{"id":"https://openalex.org/keywords/downside-risk","display_name":"Downside risk","score":0.7630019187927246},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.560519278049469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5209659337997437},{"id":"https://openalex.org/keywords/volatility","display_name":"Volatility (finance)","score":0.514754056930542},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.5044022798538208},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.43594983220100403},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4107248783111572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3234527111053467},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2907581925392151},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.2793928384780884},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.21034133434295654},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1368844211101532},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.0953511893749237}],"concepts":[{"id":"https://openalex.org/C113505986","wikidata":"https://www.wikidata.org/wiki/Q2269270","display_name":"Semivariance","level":3,"score":0.9771876335144043},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8572647571563721},{"id":"https://openalex.org/C2776719154","wikidata":"https://www.wikidata.org/wiki/Q1094965","display_name":"Downside risk","level":3,"score":0.7630019187927246},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.560519278049469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5209659337997437},{"id":"https://openalex.org/C91602232","wikidata":"https://www.wikidata.org/wiki/Q756115","display_name":"Volatility (finance)","level":2,"score":0.514754056930542},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.5044022798538208},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.43594983220100403},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4107248783111572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3234527111053467},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2907581925392151},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2793928384780884},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.21034133434295654},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1368844211101532},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0953511893749237},{"id":"https://openalex.org/C94747663","wikidata":"https://www.wikidata.org/wiki/Q7574086","display_name":"Spatial variability","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/784","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/784","pdf_url":"https://www.ijcai.org/proceedings/2023/0784.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/784","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/784","pdf_url":"https://www.ijcai.org/proceedings/2023/0784.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1058676872","display_name":null,"funder_award_id":"61425027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G184828240","display_name":null,"funder_award_id":"62192751","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1983646917","display_name":null,"funder_award_id":"62073346","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2096746888","display_name":null,"funder_award_id":"2021A1515011984","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G2247767653","display_name":null,"funder_award_id":"BNR2019TD01009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2265996673","display_name":null,"funder_award_id":"U1813216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2422091484","display_name":null,"funder_award_id":"BP2018006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G364181133","display_name":null,"funder_award_id":"2016YFB0901900","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4135978206","display_name":null,"funder_award_id":"U1811462","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4235116121","display_name":null,"funder_award_id":"CX/KJ-2020-0006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4442155276","display_name":null,"funder_award_id":"2020B1212060032","funder_id":"https://openalex.org/F4320330330","funder_display_name":"Guangdong Province Key Laboratory of Computational Science"},{"id":"https://openalex.org/G7502447764","display_name":null,"funder_award_id":"2020B1212060032","funder_id":"https://openalex.org/F4320321160","funder_display_name":"Sun Yat-sen University"},{"id":"https://openalex.org/G8330920365","display_name":null,"funder_award_id":"2017YFC0704100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8871487909","display_name":null,"funder_award_id":"11931018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321160","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71"},{"id":"https://openalex.org/F4320330330","display_name":"Guangdong Province Key Laboratory of Computational Science","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767956.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1998174418","https://openalex.org/W2017205271","https://openalex.org/W2057510529","https://openalex.org/W2081508255","https://openalex.org/W2101720440","https://openalex.org/W2132621139","https://openalex.org/W2611866857","https://openalex.org/W2766447205","https://openalex.org/W2795413297","https://openalex.org/W2806935515","https://openalex.org/W2917423723","https://openalex.org/W2951966769","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3031634197","https://openalex.org/W3035020089","https://openalex.org/W3047623911","https://openalex.org/W3123808625","https://openalex.org/W3177161388","https://openalex.org/W3192314531","https://openalex.org/W4230778209","https://openalex.org/W4283035121","https://openalex.org/W4285679304","https://openalex.org/W4288319859","https://openalex.org/W4288363736","https://openalex.org/W4293545785","https://openalex.org/W4380873470"],"related_works":["https://openalex.org/W2084157330","https://openalex.org/W164858530","https://openalex.org/W2125596750","https://openalex.org/W4388113398","https://openalex.org/W3125578341","https://openalex.org/W3126010874","https://openalex.org/W2101720440","https://openalex.org/W2519421028","https://openalex.org/W4244182608","https://openalex.org/W4251828876"],"abstract_inverted_index":{"Keeping":[0],"risk":[1,28],"under":[2,56],"control":[3,173],"is":[4,30,59,83],"often":[5],"more":[6,60],"crucial":[7],"than":[8],"maximizing":[9],"expected":[10],"rewards":[11],"in":[12,74,175],"real-world":[13],"decision-making":[14],"situations,":[15],"such":[16],"as":[17,38,40],"finance,":[18],"robotics,":[19],"autonomous":[20],"driving,":[21],"etc.":[22],"The":[23],"most":[24],"natural":[25],"choice":[26],"of":[27,52,137,181],"measures":[29],"variance,":[31],"while":[32],"it":[33],"penalizes":[34],"the":[35,41,45,70,89,93,117,126,153,158,179],"upside":[36],"volatility":[37],"much":[39],"downside":[42],"part.":[43],"Instead,":[44],"(downside)":[46],"semivariance,":[47],"which":[48,177],"captures":[49],"negative":[50],"deviation":[51],"a":[53,135,141],"random":[54],"variable":[55],"its":[57],"mean,":[58],"suitable":[61],"for":[62,121],"risk-averse":[63],"proposes.":[64],"This":[65],"paper":[66],"aims":[67],"at":[68],"optimizing":[69],"mean-semivariance":[71],"(MSV)":[72],"criterion":[73],"reinforcement":[75],"learning":[76],"w.r.t.":[77],"steady":[78],"reward":[79,143],"distribution.":[80],"Since":[81],"semivariance":[82],"time-inconsistent":[84],"and":[85,115,157],"does":[86],"not":[87],"satisfy":[88],"standard":[90],"Bellman":[91],"equation,":[92],"traditional":[94],"dynamic":[95],"programming":[96],"methods":[97],"are":[98],"inapplicable":[99],"to":[100,110,171],"MSV":[101,127],"problems":[102,139,170],"directly.":[103],"To":[104],"tackle":[105],"this":[106],"challenge,":[107],"we":[108,146,163],"resort":[109],"Perturbation":[111],"Analysis":[112],"(PA)":[113],"theory":[114,156],"establish":[116],"performance":[118],"difference":[119],"formula":[120],"MSV.":[122],"We":[123],"reveal":[124],"that":[125],"problem":[128],"can":[129],"be":[130],"solved":[131],"by":[132],"iteratively":[133],"solving":[134],"sequence":[136],"RL":[138],"with":[140],"policy-dependent":[142],"function.":[144],"Further,":[145],"propose":[147],"two":[148],"on-policy":[149],"algorithms":[150],"based":[151],"on":[152],"policy":[154],"gradient":[155],"trust":[159],"region":[160],"method.":[161],"Finally,":[162],"conduct":[164],"diverse":[165],"experiments":[166],"from":[167],"simple":[168],"bandit":[169],"continuous":[172],"tasks":[174],"MuJoCo,":[176],"demonstrate":[178],"effectiveness":[180],"our":[182],"proposed":[183],"methods.":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}