{"id":"https://openalex.org/W3035367521","doi":"https://doi.org/10.24963/ijcai.2020/396","title":"Constrained Policy Improvement for Efficient Reinforcement Learning","display_name":"Constrained Policy Improvement for Efficient Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035367521","doi":"https://doi.org/10.24963/ijcai.2020/396","mag":"3035367521"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/396","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/396","pdf_url":"https://www.ijcai.org/proceedings/2020/0396.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth 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/2020/0396.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024401360","display_name":"Elad Sarafian","orcid":"https://orcid.org/0000-0002-3271-6308"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Elad Sarafian","raw_affiliation_strings":["Bar-Ilan University","Bar-Ilan University, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020699288","display_name":"Aviv Tamar","orcid":"https://orcid.org/0000-0002-1972-854X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Aviv Tamar","raw_affiliation_strings":["Technion","Technion, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103213461","display_name":"Sarit Kraus","orcid":"https://orcid.org/0000-0003-4672-623X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sarit Kraus","raw_affiliation_strings":["Bar-Ilan University","Bar-Ilan University, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0833,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82589321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2863","last_page":"2871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987999796867371,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9955000281333923,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8928778171539307},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8908952474594116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7141127586364746},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5323354005813599},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5166912078857422},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4985501766204834},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4928896427154541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45538970828056335},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.43462276458740234},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4221191108226776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28701022267341614},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2376842498779297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15650278329849243},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11304178833961487},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.0707409679889679},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.06637650728225708}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8928778171539307},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8908952474594116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7141127586364746},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5323354005813599},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5166912078857422},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4985501766204834},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4928896427154541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45538970828056335},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.43462276458740234},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4221191108226776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28701022267341614},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2376842498779297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15650278329849243},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11304178833961487},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0707409679889679},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.06637650728225708},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/396","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/396","pdf_url":"https://www.ijcai.org/proceedings/2020/0396.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/396","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/396","pdf_url":"https://www.ijcai.org/proceedings/2020/0396.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035367521.pdf","grobid_xml":"https://content.openalex.org/works/W3035367521.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1583330603","https://openalex.org/W1771410628","https://openalex.org/W1931027396","https://openalex.org/W1986014385","https://openalex.org/W2111241577","https://openalex.org/W2112964839","https://openalex.org/W2119567691","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2752560390","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2786928559","https://openalex.org/W2787938642","https://openalex.org/W2788862220","https://openalex.org/W2951799221","https://openalex.org/W2963276097","https://openalex.org/W4214717370","https://openalex.org/W4288358463","https://openalex.org/W4289543315","https://openalex.org/W4297824719","https://openalex.org/W4301501993"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W1531601525","https://openalex.org/W1925875298","https://openalex.org/W4292701710","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"We":[0,125],"propose":[1],"a":[2,61,99,105,122],"policy":[3,47,62,76,161],"improvement":[4,58],"algorithm":[5],"for":[6],"Reinforcement":[7],"Learning":[8,134],"(RL)":[9],"termed":[10],"Rerouted":[11],"Behavior":[12],"Improvement":[13],"(RBI).":[14],"RBI":[15,71,127,154],"is":[16,72,86],"designed":[17],"to":[18,73,78,88],"take":[19],"into":[20],"account":[21],"the":[22,26,36,66,68,118,132,151],"evaluation":[23],"errors":[24,29,53],"of":[25,70,101,140,153],"Q-function.":[27],"Such":[28],"are":[30],"common":[31],"in":[32,128,131,165,170],"RL":[33,171],"when":[34,96,117],"learning":[35,97,137,166],"Q-value":[37],"from":[38,56,98,138,167],"finite":[39],"experience":[40],"data.":[41],"Greedy":[42],"policies":[43,143,157],"or":[44],"even":[45],"constrained":[46,160],"optimization":[48,162],"algorithms":[49,163],"that":[50,80,111],"ignore":[51],"these":[52],"may":[54],"suffer":[55],"an":[57],"penalty":[59],"(i.e.,":[60],"impairment).":[63],"To":[64],"reduce":[65,94],"penalty,":[67],"idea":[69],"attenuate":[74],"rapid":[75],"changes":[77],"actions":[79],"were":[81],"rarely":[82],"sampled.":[83],"This":[84],"approach":[85],"shown":[87],"avoid":[89],"catastrophic":[90],"performance":[91],"degradation":[92],"and":[93,144,158,169],"regret":[95],"batch":[100],"transition":[102],"samples.":[103],"Through":[104],"two-armed":[106],"bandit":[107],"example,":[108],"we":[109],"show":[110],"it":[112],"also":[113],"increases":[114],"data":[115],"efficiency":[116],"optimal":[119],"action":[120],"has":[121],"high":[123],"variance.":[124],"evaluate":[126],"two":[129],"tasks":[130],"Atari":[133],"Environment:":[135],"(1)":[136],"observations":[139,168],"multiple":[141],"behavior":[142],"(2)":[145],"iterative":[146],"RL.":[147],"Our":[148],"results":[149],"demonstrate":[150],"advantage":[152],"over":[155],"greedy":[156],"other":[159],"both":[164],"tasks.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}