{"id":"https://openalex.org/W4395055608","doi":"https://doi.org/10.1007/978-3-031-57963-9_3","title":"Bag of\u00a0Policies for\u00a0Distributional Deep Exploration","display_name":"Bag of\u00a0Policies for\u00a0Distributional Deep Exploration","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395055608","doi":"https://doi.org/10.1007/978-3-031-57963-9_3"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-57963-9_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-57963-9_3","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":"book-chapter","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/A5092803228","display_name":"Asen Nachkov","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Asen Nachkov","raw_affiliation_strings":["Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054395489","display_name":"Luchen Li","orcid":"https://orcid.org/0000-0002-6679-5948"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luchen Li","raw_affiliation_strings":["Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK"],"raw_orcid":"https://orcid.org/0000-0002-6679-5948","affiliations":[{"raw_affiliation_string":"Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000582003","display_name":"Giulia Luise","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giulia Luise","raw_affiliation_strings":["Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092803229","display_name":"Filippo Valdettaro","orcid":"https://orcid.org/0000-0002-9824-9378"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Filippo Valdettaro","raw_affiliation_strings":["Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK"],"raw_orcid":"https://orcid.org/0000-0002-9824-9378","affiliations":[{"raw_affiliation_string":"Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060700722","display_name":"A. Aldo Faisal","orcid":"https://orcid.org/0000-0003-0813-7207"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"A. Aldo Faisal","raw_affiliation_strings":["Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK","Chair in Digital Health and Data Science, University of Bayreuth, 95447, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0813-7207","affiliations":[{"raw_affiliation_string":"Brain and Behaviour Lab, Department of Computing, Imperial College London, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Chair in Digital Health and Data Science, University of Bayreuth, 95447, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092803228"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12064974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9853000044822693,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9778000116348267,"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":0.7454442977905273},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6969530582427979},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6788529753684998},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.6076647639274597},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5833767652511597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5782518982887268},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.523715078830719},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5078504681587219},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4778718054294586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4447654187679291},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33190131187438965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1289212703704834},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12529322504997253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454442977905273},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6969530582427979},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6788529753684998},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.6076647639274597},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5833767652511597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5782518982887268},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.523715078830719},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5078504681587219},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4778718054294586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4447654187679291},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33190131187438965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1289212703704834},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12529322504997253},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-57963-9_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-57963-9_3","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":[],"awards":[{"id":"https://openalex.org/G540806088","display_name":null,"funder_award_id":"EP/V025449/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1995945562","https://openalex.org/W2043806097","https://openalex.org/W2150468603","https://openalex.org/W2260756217","https://openalex.org/W2332257675","https://openalex.org/W2334782222","https://openalex.org/W2765302304","https://openalex.org/W2798705390","https://openalex.org/W2905224739","https://openalex.org/W2946364835","https://openalex.org/W2962718166","https://openalex.org/W2968113041","https://openalex.org/W2998069546","https://openalex.org/W3177063094","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4401386752"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}