{"id":"https://openalex.org/W2963044034","doi":"https://doi.org/10.1007/978-3-030-46133-1_4","title":"Safe Policy Improvement with Soft Baseline Bootstrapping","display_name":"Safe Policy Improvement with Soft Baseline Bootstrapping","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2963044034","doi":"https://doi.org/10.1007/978-3-030-46133-1_4","mag":"2963044034"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-46133-1_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-46133-1_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5015712624","display_name":"Kimia Nadjahi","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Kimia Nadjahi","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089214987","display_name":"Romain Laroche","orcid":"https://orcid.org/0000-0001-7180-2746"},"institutions":[{"id":"https://openalex.org/I4210153468","display_name":"Microsoft (Canada)","ror":"https://ror.org/04xhxg104","country_code":"CA","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210153468"]},{"id":"https://openalex.org/I4402554038","display_name":"Microsoft Research Montr\u00e9al (Canada)","ror":"https://ror.org/05xdft911","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4402554038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Romain Laroche","raw_affiliation_strings":["Microsoft Research Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I4210153468","https://openalex.org/I4402554038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080042640","display_name":"R\u00e9mi Tachet des Combes","orcid":"https://orcid.org/0000-0002-0763-8723"},"institutions":[{"id":"https://openalex.org/I4210153468","display_name":"Microsoft (Canada)","ror":"https://ror.org/04xhxg104","country_code":"CA","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210153468"]},{"id":"https://openalex.org/I4402554038","display_name":"Microsoft Research Montr\u00e9al (Canada)","ror":"https://ror.org/05xdft911","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4402554038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"R\u00e9mi Tachet des Combes","raw_affiliation_strings":["Microsoft Research Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I4210153468","https://openalex.org/I4402554038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015712624"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.996399998664856,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.8245814442634583},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7958675026893616},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7555795907974243},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7521388530731201},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5733726024627686},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5449950695037842},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4995157718658447},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4896853268146515},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47924068570137024},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.44624561071395874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3659270107746124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3642626404762268},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26348838210105896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10523036122322083},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.0975106954574585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245814442634583},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7958675026893616},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7555795907974243},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7521388530731201},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5733726024627686},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5449950695037842},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4995157718658447},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4896853268146515},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47924068570137024},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.44624561071395874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659270107746124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3642626404762268},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26348838210105896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10523036122322083},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0975106954574585},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-46133-1_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-46133-1_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W91593682","https://openalex.org/W166862392","https://openalex.org/W192920577","https://openalex.org/W1571051474","https://openalex.org/W1575592356","https://openalex.org/W1580157800","https://openalex.org/W1677182931","https://openalex.org/W1965878388","https://openalex.org/W2068531154","https://openalex.org/W2120346334","https://openalex.org/W2121506959","https://openalex.org/W2121863487","https://openalex.org/W2127470768","https://openalex.org/W2145339207","https://openalex.org/W2163068732","https://openalex.org/W2168565265","https://openalex.org/W2419612459","https://openalex.org/W2472245206","https://openalex.org/W2504355181","https://openalex.org/W2560674852","https://openalex.org/W2746553466","https://openalex.org/W2787236409","https://openalex.org/W2899771611","https://openalex.org/W2904450917","https://openalex.org/W2914920107","https://openalex.org/W2949608212","https://openalex.org/W2964067469","https://openalex.org/W3093206925","https://openalex.org/W4214717370","https://openalex.org/W4232295239","https://openalex.org/W4247950230","https://openalex.org/W6756040250","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W1534274833","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4318719684","https://openalex.org/W4281847915","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}