{"id":"https://openalex.org/W4407254184","doi":"https://doi.org/10.1007/978-981-97-8702-9_33","title":"Examining Policy Entropy of\u00a0Reinforcement Learning Agents for\u00a0Personalization Tasks","display_name":"Examining Policy Entropy of\u00a0Reinforcement Learning Agents for\u00a0Personalization Tasks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407254184","doi":"https://doi.org/10.1007/978-981-97-8702-9_33"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-97-8702-9_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-8702-9_33","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/A5002906983","display_name":"Anton Dereventsov","orcid":"https://orcid.org/0000-0002-7095-8236"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anton Dereventsov","raw_affiliation_strings":["Lirio AI Research, Lirio LLC, Knoxville, TN, 37830, USA"],"raw_orcid":"https://orcid.org/0000-0002-7095-8236","affiliations":[{"raw_affiliation_string":"Lirio AI Research, Lirio LLC, Knoxville, TN, 37830, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042089485","display_name":"Andrew Starnes","orcid":"https://orcid.org/0009-0004-5426-325X"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Starnes","raw_affiliation_strings":["Lirio AI Research, Lirio LLC, Knoxville, TN, 37830, USA"],"raw_orcid":"https://orcid.org/0009-0004-5426-325X","affiliations":[{"raw_affiliation_string":"Lirio AI Research, Lirio LLC, Knoxville, TN, 37830, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009338966","display_name":"Clayton Webster","orcid":"https://orcid.org/0000-0002-1375-0359"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clayton Webster","raw_affiliation_strings":["Lirio AI Research, Lirio LLC, Knoxville, TN, 37830, USA"],"raw_orcid":"https://orcid.org/0000-0002-1375-0359","affiliations":[{"raw_affiliation_string":"Lirio AI Research, Lirio LLC, Knoxville, TN, 37830, USA","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002906983"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05123722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"493","last_page":"504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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/T10603","display_name":"Smart Grid Energy Management","score":0.968999981880188,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8587937355041504},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.8285998106002808},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8231518864631653},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.486102819442749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41553497314453125},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3876529932022095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33018597960472107},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20986682176589966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587937355041504},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8285998106002808},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8231518864631653},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.486102819442749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41553497314453125},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3876529932022095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33018597960472107},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20986682176589966},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-97-8702-9_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-8702-9_33","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":[{"display_name":"Reduced inequalities","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1690919088","https://openalex.org/W1975767384","https://openalex.org/W2029604041","https://openalex.org/W2046376809","https://openalex.org/W2071133755","https://openalex.org/W2094824485","https://openalex.org/W2112420033","https://openalex.org/W2148398661","https://openalex.org/W2200988052","https://openalex.org/W2210543184","https://openalex.org/W2212290806","https://openalex.org/W2251567929","https://openalex.org/W2260756217","https://openalex.org/W2265908272","https://openalex.org/W2515895890","https://openalex.org/W2614794251","https://openalex.org/W2739757962","https://openalex.org/W2796868086","https://openalex.org/W2914272066","https://openalex.org/W2947403938","https://openalex.org/W2962898908","https://openalex.org/W2964059922","https://openalex.org/W2973184394","https://openalex.org/W3001141399","https://openalex.org/W3015197516","https://openalex.org/W3098551837","https://openalex.org/W3111523098","https://openalex.org/W3135252453","https://openalex.org/W3211540990","https://openalex.org/W4206094817","https://openalex.org/W4391583875","https://openalex.org/W6600001191","https://openalex.org/W6600104757","https://openalex.org/W6603932791","https://openalex.org/W6608373568","https://openalex.org/W6780608970","https://openalex.org/W6814003322","https://openalex.org/W6822220479"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W4306904969","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W2593798266"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
