{"id":"https://openalex.org/W4389315157","doi":"https://doi.org/10.1109/cog57401.2023.10333147","title":"Sample Efficient Reinforcement Learning with Double Importance Sampling Weight Clipping","display_name":"Sample Efficient Reinforcement Learning with Double Importance Sampling Weight Clipping","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4389315157","doi":"https://doi.org/10.1109/cog57401.2023.10333147"},"language":"en","primary_location":{"id":"doi:10.1109/cog57401.2023.10333147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Games (CoG)","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/A5111086260","display_name":"Jiale Han","orcid":"https://orcid.org/0009-0005-3928-1588"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Han","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035851949","display_name":"Mingxiao Feng","orcid":"https://orcid.org/0000-0002-7412-0481"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxiao Feng","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","institution_ids":["https://openalex.org/I4210137491"]},{"raw_affiliation_string":"Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China","institution_ids":["https://openalex.org/I4210137491"]},{"raw_affiliation_string":"Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72107053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T10663","display_name":"Advanced Battery Technologies Research","score":0.9832000136375427,"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"}},{"id":"https://openalex.org/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/clipping","display_name":"Clipping (morphology)","score":0.799534797668457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6779903769493103},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5533514022827148},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5194489359855652},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5188149809837341},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.49852991104125977},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.49313658475875854},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4108910858631134},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38405272364616394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31629297137260437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.259390652179718},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15278518199920654},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08768150210380554}],"concepts":[{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.799534797668457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779903769493103},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5533514022827148},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5194489359855652},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5188149809837341},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.49852991104125977},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.49313658475875854},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4108910858631134},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38405272364616394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31629297137260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.259390652179718},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15278518199920654},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08768150210380554},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog57401.2023.10333147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Games (CoG)","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2736601468","https://openalex.org/W2749928749","https://openalex.org/W2895031295","https://openalex.org/W2975778877","https://openalex.org/W3105045035","https://openalex.org/W3210807411","https://openalex.org/W4214717370","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6704571135","https://openalex.org/W6729507393","https://openalex.org/W6730111887","https://openalex.org/W6741002519","https://openalex.org/W6743802245","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6748839928","https://openalex.org/W6755295113","https://openalex.org/W6762263229","https://openalex.org/W6762717864","https://openalex.org/W6780559895","https://openalex.org/W6803550857"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2035130982","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Proximal":[0],"Policy":[1],"Optimization":[2],"(PPO)":[3],"is":[4],"a":[5],"stable":[6],"on-policy":[7,25,68],"policy":[8,22,133,138],"gradient":[9],"(PG)":[10],"method":[11],"thanks":[12],"to":[13,59,106,130,153],"its":[14],"clipped":[15],"importance":[16],"sampling":[17],"(IS)":[18],"weight":[19,104],"objective":[20],"of":[21,48,67,75],"improvement.":[23],"However,":[24],"PG":[26,69],"methods":[27,37,61,70],"usually":[28],"suffer":[29],"from":[30,96,135],"poor":[31],"sample":[32,41,89],"efficiency.":[33],"In":[34,54],"contrast,":[35],"off-policy":[36,76,85,93,113,124,184],"have":[38],"demonstrated":[39],"better":[40],"efficiency":[42,74,90],"by":[43,91,112,160],"making":[44],"more":[45],"effective":[46],"use":[47],"all":[49],"collected":[50],"samples":[51,94],"during":[52],"training.":[53],"this":[55,79],"work,":[56],"we":[57,81,100,141],"aim":[58],"develop":[60],"that":[62,87,173],"inherit":[63],"both":[64],"the":[65,72,108,117,127,132,136,143,150,174],"stability":[66],"and":[71,139,157,168,180],"data":[73,125],"methods.":[77],"To":[78],"end,":[80],"present":[82],"GeDISC,":[83],"an":[84],"algorithm":[86,177],"improves":[88],"reusing":[92],"drawn":[95],"prior":[97],"policies.":[98],"Besides,":[99],"propose":[101],"double":[102],"IS":[103],"clipping":[105,121,129,145,152],"control":[107,170],"high":[109,155],"instability":[110],"caused":[111],"data.":[114],"We":[115],"take":[116],"recently":[118],"proposed":[119,175],"generalized":[120],"mechanism":[122,146],"for":[123],"as":[126,149],"first":[128],"bound":[131],"update":[134],"current":[137],"meanwhile":[140],"extend":[142],"standard":[144],"in":[147],"PPO":[148,179],"second":[151],"prevent":[154],"variance":[156],"bias":[158],"brought":[159],"extremely":[161],"old":[162],"samples.":[163],"Extensive":[164],"experiments":[165],"on":[166],"continuous":[167],"discrete":[169],"tasks":[171],"show":[172],"new":[176],"outperforms":[178],"other":[181],"SOTA":[182],"PPO-based":[183],"algorithms.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}