{"id":"https://openalex.org/W4285114615","doi":"https://doi.org/10.1109/tai.2022.3185180","title":"R\u00e9nyi State Entropy Maximization for Exploration Acceleration in Reinforcement Learning","display_name":"R\u00e9nyi State Entropy Maximization for Exploration Acceleration in Reinforcement Learning","publication_year":2022,"publication_date":"2022-06-21","ids":{"openalex":"https://openalex.org/W4285114615","doi":"https://doi.org/10.1109/tai.2022.3185180"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2022.3185180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3185180","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","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/A5110921988","display_name":"Mingqi Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqi Yuan","raw_affiliation_strings":["School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040559125","display_name":"Man-On Pun","orcid":"https://orcid.org/0000-0003-3316-5381"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man-On Pun","raw_affiliation_strings":["School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3316-5381","affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391547","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0003-3144-8767"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8039,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87211703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"4","issue":"5","first_page":"1154","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.9919999837875366,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9868999719619751,"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/estimator","display_name":"Estimator","score":0.6108248233795166},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5562136173248291},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5480917692184448},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5451674461364746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5309115648269653},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.49021226167678833},{"id":"https://openalex.org/keywords/cross-entropy-method","display_name":"Cross-entropy method","score":0.48260796070098877},{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"Entropy maximization","score":0.48157668113708496},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4496307373046875},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3737148940563202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35739800333976746},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35725608468055725},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.346184641122818},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3413689136505127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32621192932128906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2686660885810852},{"id":"https://openalex.org/keywords/combinatorial-optimization","display_name":"Combinatorial optimization","score":0.2271939218044281},{"id":"https://openalex.org/keywords/quadratic-assignment-problem","display_name":"Quadratic assignment problem","score":0.11362594366073608},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09522217512130737}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6108248233795166},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5562136173248291},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5480917692184448},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5451674461364746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5309115648269653},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.49021226167678833},{"id":"https://openalex.org/C75782508","wikidata":"https://www.wikidata.org/wiki/Q3333633","display_name":"Cross-entropy method","level":4,"score":0.48260796070098877},{"id":"https://openalex.org/C127233936","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Entropy maximization","level":3,"score":0.48157668113708496},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4496307373046875},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3737148940563202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35739800333976746},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35725608468055725},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.346184641122818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3413689136505127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32621192932128906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2686660885810852},{"id":"https://openalex.org/C52692508","wikidata":"https://www.wikidata.org/wiki/Q1333872","display_name":"Combinatorial optimization","level":2,"score":0.2271939218044281},{"id":"https://openalex.org/C98036226","wikidata":"https://www.wikidata.org/wiki/Q7268356","display_name":"Quadratic assignment problem","level":3,"score":0.11362594366073608},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09522217512130737},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2022.3185180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3185180","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.4300000071525574,"display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1557517019","https://openalex.org/W1981050900","https://openalex.org/W1988526405","https://openalex.org/W2005830269","https://openalex.org/W2089943482","https://openalex.org/W2140332127","https://openalex.org/W2164424353","https://openalex.org/W2638556271","https://openalex.org/W2736601468","https://openalex.org/W2914261249","https://openalex.org/W2963523627","https://openalex.org/W3175662487","https://openalex.org/W4214717370","https://openalex.org/W6622487243","https://openalex.org/W6627932998","https://openalex.org/W6638667902","https://openalex.org/W6640963894","https://openalex.org/W6717230150","https://openalex.org/W6735033012","https://openalex.org/W6741002519","https://openalex.org/W6753925943","https://openalex.org/W6754957883","https://openalex.org/W6756303580","https://openalex.org/W6757058172","https://openalex.org/W6758978475","https://openalex.org/W6760385162","https://openalex.org/W6765240361","https://openalex.org/W6771807793","https://openalex.org/W6771968188","https://openalex.org/W6779162555","https://openalex.org/W6780559895","https://openalex.org/W6791110673"],"related_works":["https://openalex.org/W3102188974","https://openalex.org/W4287870705","https://openalex.org/W3004810941","https://openalex.org/W3199097846","https://openalex.org/W4297193174","https://openalex.org/W624081655","https://openalex.org/W2951493954","https://openalex.org/W2576492542","https://openalex.org/W1952656308","https://openalex.org/W2073182819"],"abstract_inverted_index":{"One":[0],"of":[1,17],"the":[2,13,18,34,47,94,108,113,147,155],"most":[3,40],"critical":[4],"challenges":[5],"in":[6,46,72,77],"deep":[7],"reinforcement":[8],"learning":[9,74],"is":[10,97,105,129,143],"to":[11,29,36,50,99,145,166],"maintain":[12],"long-term":[14],"exploration":[15,53],"capability":[16],"agent.":[19],"To":[20],"tackle":[21],"this":[22,85],"problem,":[23],"it":[24],"has":[25],"been":[26],"recently":[27],"proposed":[28,45,98,109,156],"provide":[30,51,100],"intrinsic":[31,42,89,102],"rewards":[32],"for":[33,131],"agent":[35],"encourage":[37],"exploration.":[38],"However,":[39],"existing":[41,114,167],"reward-based":[43],"methods":[44,65],"literature":[48],"fail":[49],"sustainable":[52],"incentives,":[54],"a":[55,87,121,135],"problem":[56],"known":[57],"as":[58,164],"vanishing":[59],"rewards.":[60,103],"In":[61,84,119],"addition,":[62],"these":[63],"conventional":[64],"incur":[66],"complex":[67],"models":[68],"and":[69,81],"additional":[70],"memory":[71],"their":[73],"procedures,":[75],"resulting":[76],"high":[78],"computational":[79],"complexity":[80],"low":[82],"robustness.":[83],"work,":[86],"novel":[88],"reward":[90],"module":[91],"based":[92],"on":[93],"R\u00e9nyi":[95,157],"entropy":[96,116,132],"high-quality":[101],"It":[104],"shown":[106],"that":[107,154],"method":[110,142,159],"actually":[111],"generalizes":[112],"state":[115],"maximization":[117],"methods.":[118],"particular,":[120],"<inline-formula":[122,136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123,137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[124,138],"notation=\"LaTeX\">$k$</tex-math></inline-formula>":[125,139],"-nearest":[126],"neighbor":[127],"estimator":[128],"introduced":[130],"estimation":[133,148],"while":[134],"-value":[140],"search":[141],"designed":[144],"guarantee":[146],"accuracy.":[149],"Extensive":[150],"simulation":[151],"results":[152],"demonstrate":[153],"entropy-based":[158],"can":[160],"achieve":[161],"higher":[162],"performance":[163],"compared":[165],"schemes.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}