{"id":"https://openalex.org/W4406612215","doi":"https://doi.org/10.1109/wsc63780.2024.10838808","title":"Distortion Risk Measure-Based Deep Reinforcement Learning","display_name":"Distortion Risk Measure-Based Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406612215","doi":"https://doi.org/10.1109/wsc63780.2024.10838808"},"language":"en","primary_location":{"id":"doi:10.1109/wsc63780.2024.10838808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc63780.2024.10838808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1871.1/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101932437","display_name":"Jinyang Jiang","orcid":"https://orcid.org/0009-0001-8192-5886"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyang Jiang","raw_affiliation_strings":["Wuhan Institute for Artificial Intelligence, Guanghua School of Management, Peking University,Beijing,CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan Institute for Artificial Intelligence, Guanghua School of Management, Peking University,Beijing,CHINA","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069167370","display_name":"Bernd Heidergott","orcid":"https://orcid.org/0000-0002-3389-2311"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bernd Heidergott","raw_affiliation_strings":["Vrije Universiteit Amsterdam,Amsterdam,THE NETHERLANDS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam,Amsterdam,THE NETHERLANDS","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088820331","display_name":"Jiaqiao Hu","orcid":"https://orcid.org/0000-0002-9999-672X"},"institutions":[{"id":"https://openalex.org/I4210131439","display_name":"Applied Mathematics (United States)","ror":"https://ror.org/03seew607","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131439"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqiao Hu","raw_affiliation_strings":["Stony Brook University,Dept. of Applied Mathematics and Statistics,Stony Brook,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University,Dept. of Applied Mathematics and Statistics,Stony Brook,NY,USA","institution_ids":["https://openalex.org/I4210131439","https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005503619","display_name":"Yijie Peng","orcid":"https://orcid.org/0000-0003-2584-8131"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Peng","raw_affiliation_strings":["Wuhan Institute for Artificial Intelligence, Guanghua School of Management, Peking University,Beijing,CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan Institute for Artificial Intelligence, Guanghua School of Management, Peking University,Beijing,CHINA","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7133,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72809237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2595","last_page":"2606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9016000032424927,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9016000032424927,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.7078725099563599},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.7020636796951294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6457268595695496},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6263257265090942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5876204967498779},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3814328610897064},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23661324381828308},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.057397544384002686}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7078725099563599},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7020636796951294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6457268595695496},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6263257265090942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5876204967498779},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3814328610897064},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23661324381828308},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.057397544384002686},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wsc63780.2024.10838808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc63780.2024.10838808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jiang, J, Heidergott, B, Hu, J & Peng, Y 2024, DISTORTION RISK MEASURE-BASED DEEP REINFORCEMENT LEARNING. in 2024 Winter Simulation Conference (WSC) : [Proceedings]. Proceedings - Winter Simulation Conference, Institute of Electrical and Electronics Engineers Inc., pp. 2595-2606, 2024 Winter Simulation Conference, WSC 2024, Orlando, United States, 15/12/24. https://doi.org/10.1109/WSC63780.2024.10838808","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jiang, J, Heidergott, B, Hu, J & Peng, Y 2024, DISTORTION RISK MEASURE-BASED DEEP REINFORCEMENT LEARNING. in 2024 Winter Simulation Conference (WSC) : [Proceedings]. Proceedings - Winter Simulation Conference, Institute of Electrical and Electronics Engineers Inc., pp. 2595-2606, 2024 Winter Simulation Conference, WSC 2024, Orlando, United States, 15/12/24. https://doi.org/10.1109/WSC63780.2024.10838808","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:research.vu.nl:publications/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","is_oa":true,"landing_page_url":"https://research.vu.nl/files/399101972/Distortion_Risk_Measure-Based_Deep_Reinforcement_Learning.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jiang, J, Heidergott, B, Hu, J & Peng, Y 2024, DISTORTION RISK MEASURE-BASED DEEP REINFORCEMENT LEARNING. in 2024 Winter Simulation Conference (WSC) : [Proceedings]. Proceedings - Winter Simulation Conference, Institute of Electrical and Electronics Engineers Inc., pp. 2595-2606, 2024 Winter Simulation Conference, WSC 2024, Orlando, United States, 15/12/24. https://doi.org/10.1109/WSC63780.2024.10838808","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:research.vu.nl:openaire/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/014b7bfd-3ecf-46f7-b031-3e38fb3fcf50","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jiang, J, Heidergott, B, Hu, J & Peng, Y 2024, DISTORTION RISK MEASURE-BASED DEEP REINFORCEMENT LEARNING. in 2024 Winter Simulation Conference (WSC) : [Proceedings]. Proceedings - Winter Simulation Conference, Institute of Electrical and Electronics Engineers Inc., pp. 2595-2606, 2024 Winter Simulation Conference, WSC 2024, Orlando, United States, 15/12/24. https://doi.org/10.1109/WSC63780.2024.10838808","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1857539435","https://openalex.org/W1985734023","https://openalex.org/W1990437501","https://openalex.org/W2041946752","https://openalex.org/W2053984877","https://openalex.org/W2067774568","https://openalex.org/W2087018957","https://openalex.org/W2092463994","https://openalex.org/W2092868272","https://openalex.org/W2099220105","https://openalex.org/W2107828625","https://openalex.org/W2124289529","https://openalex.org/W2128347943","https://openalex.org/W2141203641","https://openalex.org/W2145339207","https://openalex.org/W2283980491","https://openalex.org/W2615245331","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W3135044032","https://openalex.org/W4235667863","https://openalex.org/W4241811150","https://openalex.org/W4242439180","https://openalex.org/W4250739957","https://openalex.org/W4285213594","https://openalex.org/W4286471186","https://openalex.org/W4302033506","https://openalex.org/W4317792357","https://openalex.org/W6627932998","https://openalex.org/W6629397718","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6687063787","https://openalex.org/W6696708278","https://openalex.org/W6735641298","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6765780914","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Mainstream":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"typically":[4],"focuses":[5],"on":[6],"maximizing":[7],"expected":[8],"cumulative":[9],"rewards.":[10],"In":[11],"this":[12],"paper,":[13],"we":[14],"explore":[15],"a":[16,31,49],"risk-sensitive":[17],"RL":[18,71],"setting":[19],"where":[20],"the":[21,26,40,107,111],"objective":[22],"is":[23],"to":[24,68,85],"optimize":[25],"distortion":[27],"risk":[28,36],"measure":[29],"(DRM),":[30],"criterion":[32],"better":[33],"reflecting":[34],"human":[35],"perception.":[37],"We":[38],"parameterize":[39],"action":[41],"selection":[42],"policy":[43,51],"by":[44],"neural":[45],"networks":[46],"and":[47,89],"propose":[48],"novel":[50],"gradient":[52,87],"algorithm,":[53],"DRM-based":[54,63],"Policy":[55,65],"Optimization":[56,66],"(DPO),":[57],"along":[58],"with":[59,73],"its":[60],"accelerated":[61],"variant,":[62],"Proximal":[64],"(DPPO),":[67],"address":[69],"deep":[70],"tasks":[72],"DRM":[74,112],"objectives.":[75],"DPO":[76],"integrates":[77],"three":[78],"coupled":[79],"recursions":[80],"operating":[81],"at":[82],"different":[83],"timescales":[84],"estimate":[86],"components":[88],"update":[90],"parameters":[91],"simultaneously.":[92],"Our":[93],"experiments":[94],"provide":[95],"numerical":[96],"results":[97],"across":[98],"diverse":[99],"scenarios,":[100],"demonstrating":[101],"that":[102],"our":[103],"proposed":[104],"algorithms":[105],"outperform":[106],"existing":[108],"baselines":[109],"under":[110],"criterion.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}