{"id":"https://openalex.org/W4408354429","doi":"https://doi.org/10.1109/icassp49660.2025.10889888","title":"Regret Optimization Experience Replay in Off-Policy Reinforcement Learning","display_name":"Regret Optimization Experience Replay in Off-Policy Reinforcement Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354429","doi":"https://doi.org/10.1109/icassp49660.2025.10889888"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100436670","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-4571-4413"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013150748","display_name":"Yirong Yao","orcid":"https://orcid.org/0000-0003-4601-7716"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yirong Yao","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351716","display_name":"Wei He","orcid":"https://orcid.org/0009-0004-3424-5783"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei He","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiqun Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Niu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044733681","display_name":"Chongjun Wang","orcid":"https://orcid.org/0000-0002-2628-7033"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjun Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.5454000234603882,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.5454000234603882,"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/regret","display_name":"Regret","score":0.9155855178833008},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8751541376113892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7129548192024231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33930087089538574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24564427137374878}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9155855178833008},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8751541376113892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129548192024231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33930087089538574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24564427137374878}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2761873684","https://openalex.org/W2965043358","https://openalex.org/W2973229164","https://openalex.org/W2998202787","https://openalex.org/W3035756007","https://openalex.org/W3206282417","https://openalex.org/W4225882755","https://openalex.org/W6687681856","https://openalex.org/W6753199549","https://openalex.org/W6767047803","https://openalex.org/W6768350423","https://openalex.org/W6780559895","https://openalex.org/W6790689592","https://openalex.org/W6803771995"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W1925875298","https://openalex.org/W4292701710"],"abstract_inverted_index":{"Experience":[0,18,103],"Replay":[1,104],"(ER)":[2],"allows":[3],"Deep":[4],"Reinforcement":[5],"Learning":[6],"(RL)":[7],"agent":[8,34,63],"to":[9,24,71,82,106],"reuse":[10],"past":[11,56],"experience,":[12],"as":[13],"though":[14],"recall":[15],"the":[16,68,73,77,84,89,108,123,133],"same":[17],"repeatedly.":[19],"ER":[20],"enables":[21],"RL":[22,33],"algorithm":[23,100],"be":[25,60],"trained":[26],"by":[27],"reusing":[28],"previous":[29],"states,":[30],"so":[31],"that":[32],"can":[35],"obtain":[36],"more":[37,85],"accurate":[38],"value":[39],"estimations":[40],"and":[41,76,113],"action":[42],"selections.":[43],"Current":[44],"policy":[45,52,79,130],"algorithms":[46,131],"either":[47],"have":[48],"a":[49,96],"rule-based":[50],"replay":[51,55,69,78,99],"or":[53],"uniformly":[54],"experiences,":[57],"which":[58],"may":[59],"suboptimal.":[61],"The":[62],"is":[64,80],"updated":[65,81],"based":[66],"on":[67,132],"data":[70],"maximize":[72],"cumulative":[74],"reward,":[75],"provide":[83],"valuable":[86],"experience":[87,98],"for":[88],"agent.":[90,119],"In":[91],"this":[92],"work,":[93],"we":[94,121],"propose":[95],"novel":[97],"Regret":[101],"Minimization":[102],"(RMER),":[105],"improve":[107],"immediate":[109],"reward":[110],"via":[111],"sampling":[112],"ensure":[114],"certain":[115],"exploration":[116],"capability":[117],"of":[118,125,135],"Finally,":[120],"prove":[122],"ascendency":[124],"RMER":[126],"with":[127],"different":[128],"off-":[129],"suite":[134],"Open":[136],"AI":[137],"gym":[138],"continuous":[139],"control":[140],"tasks.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}