{"id":"https://openalex.org/W2981668237","doi":"https://doi.org/10.1109/icassp40776.2020.9054546","title":"Attention-Based Curiosity-Driven Exploration in Deep Reinforcement Learning","display_name":"Attention-Based Curiosity-Driven Exploration in Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981668237","doi":"https://doi.org/10.1109/icassp40776.2020.9054546","mag":"2981668237"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.10840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034660028","display_name":"Patrik Reizinger","orcid":"https://orcid.org/0000-0001-9861-0293"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Patrik Reizinger","raw_affiliation_strings":["Department of Control Engineering and Information Technology, Budapest University of Technology and Economics, Budapest, Hungary","Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Department of Control Engineering and Information Technology, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013735103","display_name":"M\u00e1rton Szemenyei","orcid":"https://orcid.org/0000-0003-1397-6080"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Marton Szemenyei","raw_affiliation_strings":["Department of Control Engineering and Information Technology, Budapest University of Technology and Economics, Budapest, Hungary","Budapest University of Technology and Economics, Dept. of Control Engineering and Information Technology, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Control Engineering and Information Technology, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Budapest University of Technology and Economics, Dept. of Control Engineering and Information Technology, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034660028"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.2743,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61930674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3542","last_page":"3546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9836999773979187,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9794816970825195},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7809329628944397},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7634820342063904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260336875915527},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5411812663078308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5339074730873108},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4965241551399231},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3652375638484955},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3458799123764038},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14206305146217346},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11066237092018127},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06336146593093872}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9794816970825195},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7809329628944397},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7634820342063904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260336875915527},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5411812663078308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339074730873108},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4965241551399231},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3652375638484955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3458799123764038},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14206305146217346},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11066237092018127},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06336146593093872},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.10840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10840","pdf_url":"https://arxiv.org/pdf/1910.10840","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2981668237","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.10840v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.10840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.10840","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/de0v-8990","is_oa":true,"landing_page_url":"https://doi.org/10.17023/de0v-8990","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.10840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10840","pdf_url":"https://arxiv.org/pdf/1910.10840","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2099471712","https://openalex.org/W2121863487","https://openalex.org/W2614839826","https://openalex.org/W2626778328","https://openalex.org/W2798405286","https://openalex.org/W2885550588","https://openalex.org/W2899771611","https://openalex.org/W2948199691","https://openalex.org/W2963523627","https://openalex.org/W2963966654","https://openalex.org/W2964043796","https://openalex.org/W3037207827","https://openalex.org/W6692846177","https://openalex.org/W6739901393","https://openalex.org/W6750253780","https://openalex.org/W6753925943","https://openalex.org/W6756040250","https://openalex.org/W6762863188","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2751973545","https://openalex.org/W2982393770","https://openalex.org/W3010930801","https://openalex.org/W3081661003","https://openalex.org/W3210493102","https://openalex.org/W3085832734","https://openalex.org/W3042772609","https://openalex.org/W3090196474","https://openalex.org/W3169914016","https://openalex.org/W2913879094","https://openalex.org/W2989640809","https://openalex.org/W2328358444","https://openalex.org/W2922388521","https://openalex.org/W2970909667","https://openalex.org/W2953772919","https://openalex.org/W3037636088","https://openalex.org/W3036175138","https://openalex.org/W2884970059","https://openalex.org/W3016913676","https://openalex.org/W2335959470"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"enables":[2],"to":[3,33,51,73,124],"train":[4,35],"an":[5,102],"agent":[6],"via":[7],"interaction":[8],"with":[9],"the":[10,14,19,36,43,55,75,78,105,128,139],"environment.":[11],"However,":[12],"in":[13,85,143],"majority":[15],"of":[16,45,58,77,88,104],"real-world":[17],"scenarios,":[18],"extrinsic":[20],"feedback":[21],"is":[22,50,71,82,117],"sparse":[23],"or":[24],"not":[25],"sufficient,":[26],"thus":[27],"intrinsic":[28,64],"reward":[29,65],"formulations":[30],"are":[31],"needed":[32],"successfully":[34,83],"agent.":[37],"This":[38],"work":[39],"investigates":[40],"and":[41],"extends":[42],"paradigm":[44],"curiosity-driven":[46],"exploration.":[47],"Our":[48],"aim":[49],"develop":[52],"means":[53],"for":[54,127],"better":[56],"incorporation":[57],"state-and/or":[59],"action-dependent":[60],"information":[61],"into":[62],"existing":[63],"formulations.":[66],"First,":[67],"a":[68,144],"probabilistic":[69],"approach":[70,111],"taken":[72],"exploit":[74],"advantages":[76],"attention":[79,123],"mechanism,":[80],"which":[81,148],"applied":[84],"other":[86],"domains":[87],"Deep":[89],"Learning.":[90],"Combining":[91],"them,":[92],"we":[93,136,149],"propose":[94],"new":[95,145],"methods,":[96],"such":[97],"as":[98],"Attention-aided":[99],"Advantage":[100],"Actor-Critic,":[101],"extension":[103],"Actor-Critic":[106],"framework.":[107],"Second,":[108],"another":[109],"curiosity-based":[110],"-":[112,116],"Intrinsic":[113,132],"Curiosity":[114,133],"Module":[115],"extended.":[118],"The":[119,154],"proposed":[120],"model":[121],"utilizes":[122],"emphasize":[125],"features":[126],"dynamic":[129],"models":[130],"within":[131],"Module,":[134],"moreover,":[135],"also":[137],"modify":[138],"loss":[140],"function,":[141],"resulting":[142],"curiosity":[146,152],"formulation,":[147],"call":[150],"rational":[151],"(RCM).":[153],"corresponding":[155],"implementation":[156],"can":[157],"be":[158],"found":[159],"at":[160],"https://github.com/rpatrik96/AttA2C/.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}