{"id":"https://openalex.org/W2921778527","doi":"https://doi.org/10.1007/978-3-030-46133-1_2","title":"Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics","display_name":"Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2921778527","doi":"https://doi.org/10.1007/978-3-030-46133-1_2","mag":"2921778527"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-46133-1_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-46133-1_2","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.04193","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067283098","display_name":"Denis Steckelmacher","orcid":"https://orcid.org/0000-0003-1521-8494"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Denis Steckelmacher","raw_affiliation_strings":["Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium","Vrije Universiteit Br\u00fcssel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Br\u00fcssel","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004753931","display_name":"H\u00e9l\u00e8ne Plisnier","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"H\u00e9l\u00e8ne Plisnier","raw_affiliation_strings":["Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium","Vrije Universiteit Br\u00fcssel, Brussels, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Br\u00fcssel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081436755","display_name":"Diederik M. Roijers","orcid":"https://orcid.org/0000-0002-2825-2491"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Diederik M. Roijers","raw_affiliation_strings":["VU Amsterdam, De Boelelaan 1105, 1081 HV, Amsterdam, The Netherlands","VU Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VU Amsterdam, De Boelelaan 1105, 1081 HV, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"VU Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Now\u00e9","raw_affiliation_strings":["Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium","Vrije Universiteit Br\u00fcssel, Brussels, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Br\u00fcssel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067283098"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.00326525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9769999980926514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9000878930091858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6539027690887451},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6523764133453369},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6076058745384216},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5012364387512207},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49846887588500977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4550229012966156},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.44482383131980896},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44151028990745544},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4394233822822571},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.42095544934272766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3837594985961914},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27648502588272095},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.10558551549911499},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.09042394161224365}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9000878930091858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539027690887451},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6523764133453369},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6076058745384216},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5012364387512207},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49846887588500977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4550229012966156},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.44482383131980896},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44151028990745544},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4394233822822571},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.42095544934272766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3837594985961914},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27648502588272095},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.10558551549911499},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.09042394161224365},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1007/978-3-030-46133-1_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-46133-1_2","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"},{"id":"pmh:oai:research.vu.nl:publications/c6221af8-ec0b-4cc1-9d39-67065b9c980e","is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/c6221af8-ec0b-4cc1-9d39-67065b9c980e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:1903.04193","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.04193","pdf_url":"https://arxiv.org/pdf/1903.04193","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2921778527","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1903.04193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/c6221af8-ec0b-4cc1-9d39-67065b9c980e","is_oa":false,"landing_page_url":"https://hdl.handle.net/1871.1/c6221af8-ec0b-4cc1-9d39-67065b9c980e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:128223","is_oa":false,"landing_page_url":"https://ecmlpkdd2019.org/downloads/paper/48.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:251654","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.48550/arxiv.1903.04193","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.04193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3042812281","is_oa":false,"landing_page_url":"http://ceur-ws.org/Vol-2491/abstract1.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.04193","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.04193","pdf_url":"https://arxiv.org/pdf/1903.04193","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G41336743","display_name":"Robots behaving and learning safely around humans","funder_award_id":"1SA6619N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W174941419","https://openalex.org/W569478347","https://openalex.org/W1522301498","https://openalex.org/W1575592356","https://openalex.org/W1657774708","https://openalex.org/W1771410628","https://openalex.org/W1911551976","https://openalex.org/W1931027396","https://openalex.org/W2039522160","https://openalex.org/W2076337359","https://openalex.org/W2082261506","https://openalex.org/W2091565802","https://openalex.org/W2091891040","https://openalex.org/W2097451572","https://openalex.org/W2108738385","https://openalex.org/W2112583795","https://openalex.org/W2115211925","https://openalex.org/W2119579400","https://openalex.org/W2119717200","https://openalex.org/W2141559645","https://openalex.org/W2142899754","https://openalex.org/W2155027007","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2394928340","https://openalex.org/W2554984891","https://openalex.org/W2556958149","https://openalex.org/W2562992078","https://openalex.org/W2595840341","https://openalex.org/W2612610049","https://openalex.org/W2620671107","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2807588596","https://openalex.org/W2809013025","https://openalex.org/W2899205164","https://openalex.org/W2962858248","https://openalex.org/W2963170229","https://openalex.org/W2963423916","https://openalex.org/W2963642149","https://openalex.org/W2963923407","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W4234228486","https://openalex.org/W6600450872","https://openalex.org/W6600727173","https://openalex.org/W6600829110","https://openalex.org/W6730111887","https://openalex.org/W6780559895","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2990628190","https://openalex.org/W2156347136","https://openalex.org/W2911305319","https://openalex.org/W2995031981","https://openalex.org/W3090903721","https://openalex.org/W2962902376","https://openalex.org/W3210825568","https://openalex.org/W2612795874","https://openalex.org/W3180179613","https://openalex.org/W2607992281","https://openalex.org/W3001141399","https://openalex.org/W3092578608","https://openalex.org/W2942034515","https://openalex.org/W3034761715","https://openalex.org/W3207294509","https://openalex.org/W3111464135","https://openalex.org/W3104595455","https://openalex.org/W3127139973","https://openalex.org/W2899495350","https://openalex.org/W2954149929"],"abstract_inverted_index":null,"counts_by_year":[{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}