{"id":"https://openalex.org/W2040123554","doi":"https://doi.org/10.1145/1966407.1966412","title":"Sample-efficient batch reinforcement learning for dialogue management optimization","display_name":"Sample-efficient batch reinforcement learning for dialogue management optimization","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2040123554","doi":"https://doi.org/10.1145/1966407.1966412","mag":"2040123554"},"language":"en","primary_location":{"id":"doi:10.1145/1966407.1966412","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1966407.1966412","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-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/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech Lorraine","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["Sup\u00e9lec and UMI 2958 (GeorgiaTech - CNRS), Metz, France","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec and UMI 2958 (GeorgiaTech - CNRS), Metz, France","institution_ids":["https://openalex.org/I4210089931","https://openalex.org/I102475099","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech Lorraine","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["Sup\u00e9lec, Metz, France","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031626252","display_name":"Senthilkumar Chandramohan","orcid":"https://orcid.org/0000-0002-8909-5485"},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech Lorraine","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Senthilkumar Chandramohan","raw_affiliation_strings":["Sup\u00e9lec, Metz, France","Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113975499","display_name":"Herv\u00e9 Frezza-Buet","orcid":null},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech Lorraine","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Frezza-Buet","raw_affiliation_strings":["Sup\u00e9lec and UMI 2958 (GeorgiaTech - CNRS), Metz, France","Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec and UMI 2958 (GeorgiaTech - CNRS), Metz, France","institution_ids":["https://openalex.org/I4210089931","https://openalex.org/I102475099","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065100569"],"corresponding_institution_ids":["https://openalex.org/I102475099","https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I4210089931"],"apc_list":null,"apc_paid":null,"fwci":16.6626,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.99158292,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"7","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9865999817848206,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8656458854675293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8414996862411499},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5533475875854492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5418151021003723},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5065068006515503},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5015223026275635},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4912871718406677},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4860992431640625},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44564545154571533},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4405287206172943},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4272613525390625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39526641368865967},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3136385679244995},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1584969460964203}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8656458854675293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414996862411499},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5533475875854492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418151021003723},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5065068006515503},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5015223026275635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4912871718406677},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4860992431640625},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44564545154571533},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4405287206172943},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4272613525390625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39526641368865967},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3136385679244995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1584969460964203},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1966407.1966412","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1966407.1966412","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.434.3963","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.434.3963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.metz.supelec.fr/metz/personnel/pietquin/pdf/ACM_TSLP_2011_OPMGSCHFB.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00617517v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00617517","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM - Transactions on Speech and Language Processing, 2011, 7 (3), pp.art. 7 (1-21). ⟨10.1145/1966407.1966412⟩","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1924869454","display_name":null,"funder_award_id":"216594","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W196536594","https://openalex.org/W1211946649","https://openalex.org/W1542636192","https://openalex.org/W1547105496","https://openalex.org/W1560724230","https://openalex.org/W1757949796","https://openalex.org/W1778387566","https://openalex.org/W1997696513","https://openalex.org/W2021151961","https://openalex.org/W2047192163","https://openalex.org/W2072931156","https://openalex.org/W2101308260","https://openalex.org/W2106017103","https://openalex.org/W2106547558","https://openalex.org/W2107961737","https://openalex.org/W2109504867","https://openalex.org/W2110705209","https://openalex.org/W2113442785","https://openalex.org/W2116154161","https://openalex.org/W2118556122","https://openalex.org/W2119567691","https://openalex.org/W2120346334","https://openalex.org/W2126152565","https://openalex.org/W2126810476","https://openalex.org/W2132997613","https://openalex.org/W2134051188","https://openalex.org/W2151814822","https://openalex.org/W2153290280","https://openalex.org/W2154740693","https://openalex.org/W2155898337","https://openalex.org/W2163068732","https://openalex.org/W2438667436","https://openalex.org/W2603415636","https://openalex.org/W2911283634","https://openalex.org/W2915722758","https://openalex.org/W3006656721","https://openalex.org/W3011120880","https://openalex.org/W3143835353","https://openalex.org/W3195149063","https://openalex.org/W3198350258","https://openalex.org/W4230447275","https://openalex.org/W4247446124","https://openalex.org/W4285719527","https://openalex.org/W4298023569","https://openalex.org/W4300554125","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2386410636","https://openalex.org/W2952594763","https://openalex.org/W3038962357","https://openalex.org/W4285537323","https://openalex.org/W2025663273","https://openalex.org/W1932159282","https://openalex.org/W2090698372","https://openalex.org/W4383890581"],"abstract_inverted_index":{"Spoken":[0],"Dialogue":[1],"Systems":[2],"(SDS)":[3],"are":[4,95,110,136,162],"systems":[5],"which":[6],"have":[7,76],"the":[8,19,32,35,40,49,52,56,91,117,147],"ability":[9],"to":[10,79,112,138,158],"interact":[11],"with":[12,190,194],"human":[13],"beings":[14],"using":[15,120],"natural":[16],"language":[17],"as":[18,102],"medium":[20],"of":[21,34,51,59,90,119,123,146,173],"interaction.":[22],"A":[23],"dialogue":[24,36,41,53,74,85,159,174,191,204],"policy":[25,42,71,86,129],"plays":[26],"a":[27,121,139,143,195],"crucial":[28],"role":[29],"in":[30,73,131,179],"determining":[31],"functioning":[33],"management":[37,75,160],"module.":[38],"Handcrafting":[39],"is":[43],"not":[44],"always":[45],"an":[46,81,180],"option,":[47],"considering":[48],"complexity":[50],"task":[54],"and":[55,98],"stochastic":[57],"behavior":[58],"users.":[60],"In":[61],"recent":[62],"years":[63],"approaches":[64],"based":[65],"on":[66],"Reinforcement":[67],"Learning":[68],"(RL)":[69],"for":[70,84,128,141],"optimization":[72,130,161],"been":[77],"proved":[78],"be":[80],"efficient":[82,165],"approach":[83],"optimization.":[87],"Yet":[88],"most":[89],"conventional":[92],"RL":[93],"algorithms":[94,127,135,155,177],"data":[96,208],"intensive":[97],"demand":[99],"techniques":[100],"such":[101],"user":[103,211],"simulation.":[104],"Doing":[105],"so,":[106],"additional":[107],"modeling":[108,212],"errors":[109],"likely":[111],"occur.":[113],"This":[114],"paper":[115],"explores":[116],"possibility":[118],"set":[122],"approximate":[124],"dynamic":[125],"programming":[126],"SDS.":[132],"Moreover,":[133],"these":[134,154],"combined":[137],"method":[140],"learning":[142],"sparse":[144],"representation":[145],"value":[148],"function.":[149],"Experimental":[150],"results":[151],"show":[152],"that":[153,184],"when":[156],"applied":[157],"particularly":[163],"sample":[164],",":[166,209],"since":[167],"they":[168,185,200],"learn":[169,178,187,202],"from":[170,207],"few":[171],"hundreds":[172],"examples.":[175],"These":[176],"off-policy":[181],"manner,":[182],"meaning":[183],"can":[186,201],"optimal":[188],"policies":[189,205],"examples":[192],"generated":[193],"quite":[196],"simple":[197],"strategy.":[198],"Thus":[199],"good":[203],"directly":[206],"avoiding":[210],"errors.":[213]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}