{"id":"https://openalex.org/W3153965298","doi":"https://doi.org/10.1142/s0218001421520133","title":"Reward Space Noise for Exploration in Deep Reinforcement Learning","display_name":"Reward Space Noise for Exploration in Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-04-14","ids":{"openalex":"https://openalex.org/W3153965298","doi":"https://doi.org/10.1142/s0218001421520133","mag":"3153965298"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001421520133","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001421520133","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and 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/A5002670314","display_name":"Chuxiong Sun","orcid":"https://orcid.org/0000-0002-4956-6924"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuxiong Sun","raw_affiliation_strings":["The Institute of Software, Chinese Academy of Sciences, No. 4, South Fourth Street, Zhongguancun, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Software, Chinese Academy of Sciences, No. 4, South Fourth Street, Zhongguancun, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431163","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-9048-2979"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["The Institute of Software, Chinese Academy of Sciences, No. 4, South Fourth Street, Zhongguancun, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Software, Chinese Academy of Sciences, No. 4, South Fourth Street, Zhongguancun, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340627","display_name":"Qian Li","orcid":"https://orcid.org/0000-0002-8308-9551"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qian Li","raw_affiliation_strings":["College of Computer Science and Technology, University of Technology Sydney, Broadway NSW 2007, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, University of Technology Sydney, Broadway NSW 2007, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740224","display_name":"Xiaohui Hu","orcid":"https://orcid.org/0000-0001-5717-8676"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Hu","raw_affiliation_strings":["The Institute of Software, Chinese Academy of Sciences, No. 4, South Fourth Street, Zhongguancun, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Software, Chinese Academy of Sciences, No. 4, South Fourth Street, Zhongguancun, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002670314"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":0.273,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60601175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"35","issue":"10","first_page":"2152013","last_page":"2152013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9918000102043152,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9890000224113464,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8411141633987427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7737603783607483},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7273761630058289},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6873847246170044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6246576309204102},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5786488652229309},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.467290461063385},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4577220678329468},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45393240451812744}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8411141633987427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737603783607483},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7273761630058289},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6873847246170044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6246576309204102},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5786488652229309},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.467290461063385},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4577220678329468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45393240451812744},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001421520133","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001421520133","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1981276685","https://openalex.org/W1988526405","https://openalex.org/W2017957151","https://openalex.org/W2123327324","https://openalex.org/W2124352385","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2489939061","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2963523627","https://openalex.org/W2963797557","https://openalex.org/W2974778612","https://openalex.org/W3103780890"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2389214306","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2768698792"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"challenge":[2],"for":[3,63,142],"reinforcement":[4],"learning":[5,211],"(RL)":[6],"is":[7,181],"how":[8],"to":[9,25,36,43,80,102],"achieve":[10,97],"efficient":[11,33],"exploration":[12,67,99],"in":[13,46,68,158,164,170,201],"initially":[14],"unknown":[15],"environments.":[16,48],"Most":[17],"state-of-the-art":[18],"RL":[19],"algorithms":[20],"leverage":[21],"action":[22,156,185,220],"space":[23,60],"noise":[24,61,127,154,157,180,192,215,221,231],"drive":[26],"exploration.":[27],"The":[28,149],"classical":[29],"strategies":[30],"are":[31,78,140,216],"computationally":[32],"and":[34,65,86,100,113,128,161,199,210,236],"straightforward":[35],"implement.":[37],"However,":[38],"these":[39],"methods":[40],"may":[41],"fail":[42],"perform":[44],"effectively":[45],"complex":[47,103],"To":[49,109],"address":[50],"this":[51],"issue,":[52],"we":[53,77,119,167],"propose":[54],"a":[55,121,134],"novel":[56],"strategy":[57],"named":[58],"reward":[59,75,126,153,179,191,214,230],"(RSN)":[62],"farsighted":[64],"consistent":[66,98,237],"RL.":[69],"By":[70],"introducing":[71],"the":[72,93,111,116,143,171,174,190,196,203,207,223,229],"stochasticity":[73],"from":[74],"space,":[76],"able":[79],"change":[81],"agent\u2019s":[82],"understanding":[83],"about":[84],"environment":[85],"perturb":[87],"its":[88,130],"behaviors.":[89],"We":[90],"find":[91],"that":[92,152,169,189,228],"simple":[94],"RSN":[95],"can":[96,193,232],"scale":[101],"domains":[104],"without":[105],"intensive":[106],"computational":[107],"cost.":[108],"demonstrate":[110],"effectiveness":[112],"scalability":[114],"of":[115,136,178,213],"proposed":[117],"method,":[118],"implement":[120],"deep":[122],"Q-learning":[123],"agent":[124],"with":[125],"evaluate":[129],"exploratory":[131,176],"performance":[132,177],"on":[133],"set":[135],"Atari":[137],"games":[138,160],"which":[139,187,226],"challenging":[141],"naive":[144],"[Formula:":[145],"see":[146],"text]-greedy":[147],"strategy.":[148],"results":[150],"show":[151],"outperforms":[155],"most":[159],"performs":[162],"comparably":[163],"others.":[165],"Concretely,":[166],"found":[168],"early":[172],"training,":[173,225],"best":[175],"obviously":[182],"better":[183],"than":[184,219],"noise,":[186],"demonstrates":[188],"quickly":[194],"explore":[195],"valuable":[197],"states":[198],"aid":[200],"finding":[202],"optimal":[204],"policy.":[205],"Moreover,":[206],"average":[208],"scores":[209],"efficiency":[212],"also":[217],"higher":[218],"through":[222],"whole":[224],"indicates":[227],"generate":[233],"more":[234],"stable":[235],"performance.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}