{"id":"https://openalex.org/W4383982036","doi":"https://doi.org/10.1561/2200000097","title":"Reinforcement Learning, Bit by Bit","display_name":"Reinforcement Learning, Bit by Bit","publication_year":2023,"publication_date":"2023-07-11","ids":{"openalex":"https://openalex.org/W4383982036","doi":"https://doi.org/10.1561/2200000097"},"language":"en","primary_location":{"id":"doi:10.1561/2200000097","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000097","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","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/A5027358754","display_name":"Xiuyuan Lu","orcid":"https://orcid.org/0000-0001-6376-8584"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiuyuan Lu","raw_affiliation_strings":["DeepMind","DeepMind, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045543562","display_name":"Benjamin Van Roy","orcid":"https://orcid.org/0000-0001-8364-3746"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benjamin Van Roy","raw_affiliation_strings":["DeepMind","DeepMind, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085692306","display_name":"Vikranth Dwaracherla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vikranth Dwaracherla","raw_affiliation_strings":["DeepMind","DeepMind, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027959626","display_name":"Morteza Ibrahimi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Morteza Ibrahimi","raw_affiliation_strings":["DeepMind","DeepMind, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015899120","display_name":"Ian Osband","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian Osband","raw_affiliation_strings":["DeepMind","DeepMind, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067555437","display_name":"Zheng Wen","orcid":"https://orcid.org/0000-0001-6987-6463"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Wen","raw_affiliation_strings":["DeepMind","DeepMind, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":2.0621,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88817027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"6","first_page":"733","last_page":"865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.09300000220537186,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.09300000220537186,"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/bit","display_name":"Bit (key)","score":0.9523232579231262},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6502007246017456},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5328201651573181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5194201469421387},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3978438377380371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26158928871154785},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24230313301086426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1085117757320404},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10581597685813904},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08699855208396912}],"concepts":[{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.9523232579231262},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6502007246017456},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5328201651573181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5194201469421387},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3978438377380371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26158928871154785},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24230313301086426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1085117757320404},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10581597685813904},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08699855208396912}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1561/2200000097","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000097","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1862757251","https://openalex.org/W1977898558","https://openalex.org/W1988360637","https://openalex.org/W2001863269","https://openalex.org/W2003996846","https://openalex.org/W2009551863","https://openalex.org/W2016647253","https://openalex.org/W2041367235","https://openalex.org/W2049934117","https://openalex.org/W2054940200","https://openalex.org/W2069034916","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2145339207","https://openalex.org/W2149721706","https://openalex.org/W2168405694","https://openalex.org/W2236244207","https://openalex.org/W2332257675","https://openalex.org/W2489939061","https://openalex.org/W2499226730","https://openalex.org/W2765733960","https://openalex.org/W2767767619","https://openalex.org/W2978435634","https://openalex.org/W2989847975","https://openalex.org/W4206547457","https://openalex.org/W4229739354","https://openalex.org/W4234228486"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2411923897","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"agents":[2,27,78],"have":[3],"demonstrated":[4],"remarkable":[5],"achievements":[6],"in":[7],"simulated":[8],"environments.":[9,22],"Data":[10],"efficiency":[11],"poses":[12],"an":[13],"impediment":[14],"to":[15,20,60,63,70],"carrying":[16],"this":[17],"success":[18],"over":[19],"real":[21],"The":[23],"design":[24,76],"of":[25,33,51,57],"data-efficient":[26],"calls":[28],"for":[29],"a":[30],"deeper":[31],"understanding":[32],"information":[34,59,69],"acquisition":[35],"and":[36,41,67,83],"representation.":[37],"We":[38],"discuss":[39],"concepts":[40],"regret":[42],"analysis":[43],"that":[44,65,79,87],"together":[45],"offer":[46],"principled":[47],"guidance.":[48],"This":[49],"line":[50],"thinking":[52],"sheds":[53],"light":[54],"on":[55,81],"questions":[56],"what":[58,68],"seek,":[61],"how":[62],"seek":[64],"information,":[66],"retain.":[71],"To":[72],"illustrate":[73],"concepts,":[74],"we":[75],"simple":[77],"build":[80],"them":[82],"present":[84],"computational":[85],"results":[86],"highlight":[88],"data":[89],"efficiency.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}