{"id":"https://openalex.org/W4365794621","doi":"https://doi.org/10.1007/978-981-99-1642-9_13","title":"Disentangling Exploration and\u00a0Exploitation in\u00a0Deep Reinforcement Learning Using Contingency Awareness","display_name":"Disentangling Exploration and\u00a0Exploitation in\u00a0Deep Reinforcement Learning Using Contingency Awareness","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4365794621","doi":"https://doi.org/10.1007/978-981-99-1642-9_13"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-99-1642-9_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-99-1642-9_13","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information 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/A5039644451","display_name":"Ionel Hosu","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Ionel Hosu","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077365712","display_name":"Traian Rebedea","orcid":"https://orcid.org/0000-0002-7255-5537"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Traian Rebedea","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077419846","display_name":"\u0218tefan Tr\u0103u\u0219an-Matu","orcid":"https://orcid.org/0000-0001-8082-8497"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"\u0218tefan Tr\u0103u\u0219an-Matu","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039644451"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09900655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9896000027656555,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contingency","display_name":"Contingency","score":0.9098255634307861},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7676407098770142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6492689847946167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5211443901062012},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4612520933151245},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41476157307624817},{"id":"https://openalex.org/keywords/contingency-theory","display_name":"Contingency theory","score":0.4100933074951172},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37479114532470703},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.33828333020210266},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22001972794532776},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.1340911090373993},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06412696838378906}],"concepts":[{"id":"https://openalex.org/C97508593","wikidata":"https://www.wikidata.org/wiki/Q1359069","display_name":"Contingency","level":2,"score":0.9098255634307861},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7676407098770142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492689847946167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5211443901062012},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4612520933151245},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41476157307624817},{"id":"https://openalex.org/C60297154","wikidata":"https://www.wikidata.org/wiki/Q1434943","display_name":"Contingency theory","level":2,"score":0.4100933074951172},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37479114532470703},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33828333020210266},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22001972794532776},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.1340911090373993},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06412696838378906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-99-1642-9_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-99-1642-9_13","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5199999809265137,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2150468603","https://openalex.org/W2561776174","https://openalex.org/W2899077443","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2996695841","https://openalex.org/W6609741587","https://openalex.org/W6775522024","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2090010174","https://openalex.org/W2029497572","https://openalex.org/W2320126197","https://openalex.org/W1974731633","https://openalex.org/W2116050589","https://openalex.org/W3197732095","https://openalex.org/W4253661553","https://openalex.org/W2375002256","https://openalex.org/W2073022112","https://openalex.org/W2610924862"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
