{"id":"https://openalex.org/W3090196474","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207295","title":"Stochastic Curiosity Maximizing Exploration","display_name":"Stochastic Curiosity Maximizing Exploration","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090196474","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207295","mag":"3090196474"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101002202","display_name":"Po-Chien Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Chien Hsu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9628000259399414,"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/curiosity","display_name":"Curiosity","score":0.8637145757675171},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7764369249343872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7630136609077454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6470184326171875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5889990329742432}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8637145757675171},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7764369249343872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630136609077454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6470184326171875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5889990329742432},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W326419249","https://openalex.org/W1522301498","https://openalex.org/W1569296262","https://openalex.org/W1757796397","https://openalex.org/W1959608418","https://openalex.org/W2100677568","https://openalex.org/W2119717200","https://openalex.org/W2136144249","https://openalex.org/W2139612737","https://openalex.org/W2143958939","https://openalex.org/W2145339207","https://openalex.org/W2149757909","https://openalex.org/W2164411961","https://openalex.org/W2187089797","https://openalex.org/W2405331948","https://openalex.org/W2417786368","https://openalex.org/W2440926996","https://openalex.org/W2739936944","https://openalex.org/W2751973545","https://openalex.org/W2766329790","https://openalex.org/W2772217324","https://openalex.org/W2783047733","https://openalex.org/W2889008527","https://openalex.org/W2951266961","https://openalex.org/W2962717849","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964411643","https://openalex.org/W2973112754","https://openalex.org/W3015301038","https://openalex.org/W3033736971","https://openalex.org/W3041202696","https://openalex.org/W3189092450","https://openalex.org/W4297806413","https://openalex.org/W4298857966","https://openalex.org/W6631190155","https://openalex.org/W6634103402","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6692846177","https://openalex.org/W6716474083","https://openalex.org/W6718190810","https://openalex.org/W6746188011","https://openalex.org/W6747837047","https://openalex.org/W6750253780","https://openalex.org/W6754395538","https://openalex.org/W6764214684","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,13,28,45,112],"(RL)":[3],"is":[4,60,64,96,145,186],"known":[5],"as":[6,121,177],"an":[7,29,38,69],"emerging":[8],"research":[9],"trend":[10],"in":[11,72,159,169,214],"machine":[12],"for":[14,27,197],"autonomous":[15],"systems.":[16],"In":[17],"real-world":[18],"scenarios,":[19],"the":[20,25,44,50,54,57,77,83,100,105,117,126,132,149,157,166,170,178,208,211],"extrinsic":[21],"rewards,":[22],"acquired":[23],"from":[24],"environment":[26],"agent,":[30],"are":[31,175],"usually":[32],"missing":[33],"or":[34],"extremely":[35],"sparse.":[36],"Such":[37],"issue":[39],"of":[40,47,210],"sparse":[41,78,127],"reward":[42,79,128],"constrains":[43],"capability":[46],"agent":[48,51,84,118,133,182],"because":[49],"only":[52],"updates":[53],"policy":[55,92],"when":[56,94],"goal":[58],"state":[59],"successfully":[61],"attained.":[62],"It":[63],"always":[65],"challenging":[66],"to":[67,89,115,119,134,147,155,193],"implement":[68],"efficient":[70],"exploration":[71,109],"RL":[73],"algorithms.":[74],"To":[75,138],"tackle":[76],"and":[80,152,165,173,203,217],"inefficient":[81],"exploration,":[82],"needs":[85],"other":[86],"helpful":[87],"information":[88,164],"update":[90],"its":[91],"even":[93],"there":[95],"no":[97],"interaction":[98],"with":[99,125],"environment.":[101],"This":[102],"paper":[103],"proposes":[104],"stochastic":[106],"curiosity":[107],"maximizing":[108,190],"(SCME),":[110],"a":[111,141],"strategy":[113],"explored":[114],"allow":[116],"act":[120],"human.":[122],"We":[123],"cope":[124],"problem":[129],"by":[130,189],"encouraging":[131],"explore":[135],"future":[136,160],"diversity.":[137],"do":[139],"so,":[140],"latent":[142,150,153],"dynamic":[143],"system":[144,216],"developed":[146],"acquire":[148],"states":[151,172],"actions":[154,174],"predict":[156],"variations":[158],"conditions.":[161],"The":[162,181,199],"mutual":[163],"prediction":[167],"error":[168],"predicted":[171],"calculated":[176],"intrinsic":[179],"rewards.":[180],"based":[183],"on":[184,201],"SCME":[185,213],"therefore":[187],"learned":[188],"these":[191],"rewards":[192],"improve":[194],"sample":[195],"efficiency":[196],"exploration.":[198],"experiments":[200],"PyDial":[202],"Super":[204],"Mario":[205],"Bros":[206],"show":[207],"benefits":[209],"proposed":[212],"dialogue":[215],"computer":[218],"game,":[219],"respectively.":[220]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}