{"id":"https://openalex.org/W4224924677","doi":"https://doi.org/10.1109/icassp43922.2022.9746211","title":"Efficient and Stable Information Directed Exploration for Continuous Reinforcement Learning","display_name":"Efficient and Stable Information Directed Exploration for Continuous Reinforcement Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224924677","doi":"https://doi.org/10.1109/icassp43922.2022.9746211"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746211","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072241033","display_name":"Mingzhe Chen","orcid":"https://orcid.org/0000-0003-2570-703X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Mingzhe Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600503","display_name":"Xi Xiao","orcid":"https://orcid.org/0000-0003-1521-9542"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Xi Xiao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072408261","display_name":"Wanpeng Zhang","orcid":"https://orcid.org/0000-0001-5351-3449"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Wanpeng Zhang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101619331","display_name":"Xiaotian Gao","orcid":"https://orcid.org/0000-0002-2233-8200"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotian Gao","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5191,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61510734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"17","issue":null,"first_page":"4023","last_page":"4027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9952999949455261,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9419435262680054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7824133634567261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6344747543334961},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5980994701385498},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.530236005783081},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48124217987060547},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4631563723087311},{"id":"https://openalex.org/keywords/information-gain","display_name":"Information gain","score":0.4429548680782318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08890083432197571}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9419435262680054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824133634567261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6344747543334961},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5980994701385498},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.530236005783081},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48124217987060547},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4631563723087311},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.4429548680782318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08890083432197571},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746211","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"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},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320337986","display_name":"Tsinghua Shenzhen International Graduate School","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2009551863","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2168405694","https://openalex.org/W2280163991","https://openalex.org/W2342662072","https://openalex.org/W2604960773","https://openalex.org/W2765733960","https://openalex.org/W2766447205","https://openalex.org/W2767313115","https://openalex.org/W2781726626","https://openalex.org/W2787284768","https://openalex.org/W2950564923","https://openalex.org/W2963864421","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3124816456","https://openalex.org/W3172115140","https://openalex.org/W4206547457","https://openalex.org/W4234228486","https://openalex.org/W4289107544","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6704571135","https://openalex.org/W6735939104","https://openalex.org/W6745497480","https://openalex.org/W6747473740","https://openalex.org/W6747994166","https://openalex.org/W6757560991","https://openalex.org/W6763990646","https://openalex.org/W6772005887","https://openalex.org/W6780559895","https://openalex.org/W6780571964","https://openalex.org/W6789305357"],"related_works":["https://openalex.org/W2350209916","https://openalex.org/W2475524763","https://openalex.org/W2363851383","https://openalex.org/W2354517252","https://openalex.org/W2387460998","https://openalex.org/W2356631479","https://openalex.org/W2386467653","https://openalex.org/W1811296007","https://openalex.org/W2482596426","https://openalex.org/W4386266213"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,46],"investigate":[4],"the":[5,14,23,30,36,43,58,65],"exploration-exploitation":[6],"dilemma":[7],"of":[8,26,64],"reinforcement":[9,32],"learning":[10,38,52],"algorithms.":[11],"We":[12],"adapt":[13],"information":[15,24],"directed":[16],"sampling,":[17],"an":[18],"exploration":[19],"framework":[20],"that":[21,71],"measures":[22],"gain":[25],"a":[27,50],"policy,":[28],"to":[29,48,55],"continuous":[31],"learning.":[33],"To":[34],"stabilize":[35],"off-policy":[37],"process":[39],"and":[40,54,79],"further":[41],"improve":[42],"sample":[44],"efficiency,":[45],"propose":[47],"use":[49],"randomized":[51],"target":[53],"dynamically":[56],"adjust":[57],"update-to-data":[59],"ratio":[60],"for":[61],"different":[62],"parts":[63],"neural":[66],"network":[67],"model.":[68],"Experiments":[69],"show":[70],"our":[72],"approach":[73],"significantly":[74],"improves":[75],"over":[76],"existing":[77],"methods":[78],"successfully":[80],"completes":[81],"tasks":[82],"with":[83],"highly":[84],"sparse":[85],"reward":[86],"signals.":[87]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}