{"id":"https://openalex.org/W4385767841","doi":"https://doi.org/10.24963/ijcai.2023/502","title":"On the Reuse Bias in Off-Policy Reinforcement Learning","display_name":"On the Reuse Bias in Off-Policy Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767841","doi":"https://doi.org/10.24963/ijcai.2023/502"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/502","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/502","pdf_url":"https://www.ijcai.org/proceedings/2023/0502.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0502.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102656708","display_name":"Chengyang Ying","orcid":null},"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":true,"raw_author_name":"Chengyang Ying","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069363081","display_name":"Zhongkai Hao","orcid":null},"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":"Zhongkai Hao","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060724443","display_name":"Xinning Zhou","orcid":null},"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":"Xinning Zhou","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341885","display_name":"Hang Su","orcid":"https://orcid.org/0000-0001-8294-6315"},"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":"Hang Su","raw_affiliation_strings":["Pazhou Laboratory","Tsinghua University","Pazhou Laboratory; Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Pazhou Laboratory","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Pazhou Laboratory; Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080233678","display_name":"Dong Yan","orcid":"https://orcid.org/0000-0003-4549-9469"},"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":"Dong Yan","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606995","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-6254-2388"},"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":"Jun Zhu","raw_affiliation_strings":["Pazhou Laboratory","Tsinghua University","Pazhou Laboratory; Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Pazhou Laboratory","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Pazhou Laboratory; Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102656708"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3439,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6541913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4513","last_page":"4521"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/reuse","display_name":"Reuse","score":0.7888727188110352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7710065841674805},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6806255578994751},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6375924348831177},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5662185549736023},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.553972601890564},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5264210104942322},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4865204691886902},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.48387444019317627},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.44020509719848633},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.39526206254959106},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3793420195579529},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37107211351394653},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.19735172390937805},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17218515276908875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1431894600391388},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07786992192268372},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0760500431060791}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7888727188110352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710065841674805},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6806255578994751},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6375924348831177},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5662185549736023},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.553972601890564},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5264210104942322},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4865204691886902},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.48387444019317627},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.44020509719848633},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.39526206254959106},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3793420195579529},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37107211351394653},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.19735172390937805},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17218515276908875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1431894600391388},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07786992192268372},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0760500431060791},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/502","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/502","pdf_url":"https://www.ijcai.org/proceedings/2023/0502.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.2023/502","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/502","pdf_url":"https://www.ijcai.org/proceedings/2023/0502.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":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1151522064","display_name":null,"funder_award_id":"U19A2","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1614471940","display_name":null,"funder_award_id":"2020AAA0","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G162864083","display_name":null,"funder_award_id":"U19A2081","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1948779041","display_name":null,"funder_award_id":"62076147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2352870162","display_name":null,"funder_award_id":"62106123","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3178445835","display_name":null,"funder_award_id":"2020AAA0106302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3763772386","display_name":null,"funder_award_id":"2020AAA0106302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4381173361","display_name":null,"funder_award_id":"2020AAA0104304","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5372072380","display_name":null,"funder_award_id":"U1811461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5379697419","display_name":null,"funder_award_id":"62061136001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5777954143","display_name":null,"funder_award_id":"61972224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G623247002","display_name":null,"funder_award_id":"61136001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6645987955","display_name":null,"funder_award_id":"U19B2034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7164151747","display_name":null,"funder_award_id":"U181146","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/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767841.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W191658262","https://openalex.org/W607505555","https://openalex.org/W1514587017","https://openalex.org/W1600046456","https://openalex.org/W1607832978","https://openalex.org/W1811750039","https://openalex.org/W1845972764","https://openalex.org/W2014384147","https://openalex.org/W2063471322","https://openalex.org/W2107741520","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2234859443","https://openalex.org/W2273088453","https://openalex.org/W2340679559","https://openalex.org/W2595801589","https://openalex.org/W2740020751","https://openalex.org/W2746553466","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2807306981","https://openalex.org/W2883207481","https://openalex.org/W2890022552","https://openalex.org/W2890597452","https://openalex.org/W2904453761","https://openalex.org/W2948416696","https://openalex.org/W2951470703","https://openalex.org/W2962802563","https://openalex.org/W2963482016","https://openalex.org/W2963864421","https://openalex.org/W3012148463","https://openalex.org/W3033324992","https://openalex.org/W3035901905","https://openalex.org/W3103383763","https://openalex.org/W3121758515","https://openalex.org/W3132054471","https://openalex.org/W3161330381","https://openalex.org/W3166948032","https://openalex.org/W3169292790","https://openalex.org/W3170313385","https://openalex.org/W3172360140","https://openalex.org/W3183892796","https://openalex.org/W3211545083","https://openalex.org/W3212207126","https://openalex.org/W3212929567","https://openalex.org/W4285606945","https://openalex.org/W4287199936","https://openalex.org/W4287688953","https://openalex.org/W4287755399","https://openalex.org/W4289543315","https://openalex.org/W4289753142","https://openalex.org/W4293801385","https://openalex.org/W4297684135","https://openalex.org/W4298101950","https://openalex.org/W6791858558","https://openalex.org/W6803771590","https://openalex.org/W6847742374"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2353602216","https://openalex.org/W2024136090","https://openalex.org/W3169016980"],"abstract_inverted_index":{"Importance":[0,168],"sampling":[1],"(IS)":[2],"is":[3,54],"a":[4,58,125,163,214],"popular":[5],"technique":[6],"in":[7,16,69,105,220],"off-policy":[8,70,89,155],"evaluation,":[9],"which":[10,111,176],"re-weights":[11],"the":[12,17,42,52,67,74,77,88,94,98,101,109,120,130,140,145,150,179,183,194,210],"return":[13],"of":[14,44,61,64,76,93,108,129,139,152,182,216],"trajectories":[15],"replay":[18,78,102],"buffer":[19,79,103],"to":[20,34,57],"boost":[21],"sample":[22,211],"efficiency.":[23],"However,":[24],"training":[25],"with":[26,97,173],"IS":[27,65],"can":[28,143,177,191,207],"be":[29],"unstable":[30],"and":[31,82,91,118,133,186],"previous":[32],"attempts":[33],"address":[35],"this":[36,47],"issue":[37],"mainly":[38],"focus":[39],"on":[40,158,213],"analyzing":[41],"variance":[43],"IS.":[45],"In":[46],"paper,":[48],"we":[49,161],"reveal":[50],"that":[51,87,135,188,203],"instability":[53],"also":[55],"related":[56],"new":[59],"notion":[60],"Reuse":[62,131,146,184,195],"Bias":[63,132,147,196],"---":[66],"bias":[68],"evaluation":[71,81,90],"caused":[72],"by":[73,148],"reuse":[75],"for":[80,154],"optimization.":[83],"We":[84,122],"theoretically":[85],"show":[86,134,187,202],"optimization":[92],"current":[95],"policy":[96],"data":[99],"from":[100],"result":[104],"an":[106,114],"overestimation":[107],"objective,":[110],"may":[112],"cause":[113],"erroneous":[115],"gradient":[116],"update":[117],"degenerate":[119],"performance.":[121],"further":[123],"provide":[124],"high-probability":[126],"upper":[127,141],"bound":[128,142],"controlling":[136],"one":[137],"term":[138],"control":[144,218],"introducing":[149],"concept":[151],"stability":[153],"algorithms.":[156],"Based":[157],"these":[159],"analyses,":[160],"present":[162],"novel":[164],"yet":[165],"simple":[166],"Bias-Regularized":[167],"Sampling":[169],"(BIRIS)":[170],"framework":[171],"along":[172],"practical":[174],"algorithms,":[175],"alleviate":[178],"negative":[180],"impact":[181],"Bias,":[185],"our":[189,204],"BIRIS":[190],"significantly":[192,208],"reduce":[193],"empirically.":[197],"Moreover,":[198],"extensive":[199],"experimental":[200],"results":[201],"BIRIS-based":[205],"methods":[206],"improve":[209],"efficiency":[212],"series":[215],"continuous":[217],"tasks":[219],"MuJoCo.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}