{"id":"https://openalex.org/W4389623104","doi":"https://doi.org/10.1142/s0218001423510217","title":"Self-Supervised Network Distillation for Exploration","display_name":"Self-Supervised Network Distillation for Exploration","publication_year":2023,"publication_date":"2023-12-12","ids":{"openalex":"https://openalex.org/W4389623104","doi":"https://doi.org/10.1142/s0218001423510217"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001423510217","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001423510217","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/A5051493240","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-9250-8981"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["College of Software Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Software Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082017587","display_name":"Ruiyu Dai","orcid":"https://orcid.org/0009-0003-3000-247X"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruiyu Dai","raw_affiliation_strings":["College of Computer and Information Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027602901","display_name":"Weisi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weisi Chen","raw_affiliation_strings":["College of Software Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Software Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054808481","display_name":"Jiguang Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiguang Qiu","raw_affiliation_strings":["College of Software Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Software Engineering, Xiamen University of Technology, 600 Ligong Road, Xiamen 361000/Jimei District, P. R. China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082017587"],"corresponding_institution_ids":["https://openalex.org/I75867142"],"apc_list":null,"apc_paid":null,"fwci":0.174,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59343942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"37","issue":"15","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9987999796867371,"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/T12676","display_name":"Machine Learning and ELM","score":0.9987999796867371,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/initialization","display_name":"Initialization","score":0.8823692798614502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7602840662002563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7159859538078308},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.653108537197113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6290848255157471},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6288914084434509},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6229101419448853}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8823692798614502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602840662002563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7159859538078308},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.653108537197113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6290848255157471},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6288914084434509},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6229101419448853},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001423510217","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001423510217","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":[{"score":0.4399999976158142,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2085754318","https://openalex.org/W2963523627","https://openalex.org/W4220747123","https://openalex.org/W4283806682","https://openalex.org/W4319082292"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W2977257638","https://openalex.org/W4226466875","https://openalex.org/W4288095186","https://openalex.org/W3210541621"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"is":[2,31,168],"currently":[3],"applicable":[4],"across":[5],"a":[6,32,64,126],"range":[7],"of":[8,74,110,132,174],"domains,":[9],"including":[10],"robotics,":[11],"gaming,":[12],"and":[13,49,121,177],"natural":[14],"language":[15],"processing.":[16],"However,":[17],"the":[18,41,50,57,72,83,100,108,111,130,133,146,157,164],"approach":[19],"faces":[20],"difficulties":[21],"in":[22,87,117,172],"environments":[23],"with":[24,99],"sparse":[25,88],"rewards.":[26],"Random":[27],"network":[28,66,102,166],"distillation":[29,67,94,167],"(RND)":[30],"good":[33],"intrinsic":[34,97,122,152],"reward":[35,89,153],"solution":[36],"to":[37,145],"this":[38,138],"problem.":[39],"Nevertheless,":[40],"RND":[42,171],"method\u2019s":[43],"effectiveness":[44],"hinges":[45],"on":[46,52,77,129],"excellent":[47],"initialization,":[48],"reliance":[51,76],"random":[53,79],"features":[54],"somewhat":[55],"constrains":[56],"agent\u2019s":[58,84],"exploration":[59,69,85,175],"capabilities.":[60],"This":[61],"paper":[62],"proposes":[63],"self-supervised":[65,105,165],"(SSND)":[68],"method,":[70],"addressing":[71],"drawbacks":[73],"RND\u2019s":[75],"initializing":[78],"networks":[80],"while":[81],"enhancing":[82],"capability":[86],"environments.":[90],"The":[91],"method":[92],"uses":[93],"error":[95],"as":[96],"rewards,":[98,123],"target":[101,147,158],"trained":[103],"using":[104],"learning.":[106],"During":[107],"training":[109],"predictor":[112],"network,":[113,148],"we":[114,140],"noticed":[115],"fluctuations":[116],"both":[118],"loss":[119],"values":[120],"which":[124,149],"have":[125],"detrimental":[127],"impact":[128],"performance":[131],"intelligent":[134],"agent.":[135],"To":[136],"resolve":[137],"issue,":[139],"introduce":[141],"batch":[142],"normalization":[143],"layers":[144],"helps":[150],"mitigate":[151],"anomalies":[154],"stemming":[155],"from":[156],"network\u2019s":[159],"instability.":[160],"Experiments":[161],"show":[162],"that":[163],"better":[169],"than":[170],"terms":[173],"speed":[176],"performance.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}