{"id":"https://openalex.org/W2982333597","doi":"https://doi.org/10.1109/tnnls.2021.3105140","title":"VASE: Variational Assorted Surprise Exploration for Reinforcement Learning","display_name":"VASE: Variational Assorted Surprise Exploration for Reinforcement Learning","publication_year":2021,"publication_date":"2021-08-26","ids":{"openalex":"https://openalex.org/W2982333597","doi":"https://doi.org/10.1109/tnnls.2021.3105140","mag":"2982333597","pmid":"https://pubmed.ncbi.nlm.nih.gov/34437073"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3105140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3105140","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.14351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028753453","display_name":"Haitao Xu","orcid":"https://orcid.org/0000-0001-5616-1338"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Haitao Xu","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","Univ of Otago"],"raw_orcid":"https://orcid.org/0000-0001-5616-1338","affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"Univ of Otago","institution_ids":["https://openalex.org/I80281795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025970904","display_name":"Lech Szymanski","orcid":"https://orcid.org/0000-0002-5192-0304"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Lech Szymanski","raw_affiliation_strings":["Department of Computer Science, University of Otago, Dunedin, New Zealand","Univ of Otago"],"raw_orcid":"https://orcid.org/0000-0002-5192-0304","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"Univ of Otago","institution_ids":["https://openalex.org/I80281795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045878695","display_name":"Brendan McCane","orcid":"https://orcid.org/0000-0001-8055-3331"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Brendan McCane","raw_affiliation_strings":["Department of Computer Science, University of Otago, Dunedin, New Zealand","Univ of Otago"],"raw_orcid":"https://orcid.org/0000-0001-8055-3331","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"Univ of Otago","institution_ids":["https://openalex.org/I80281795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80281795"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.00432702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"34","issue":"3","first_page":"1243","last_page":"1252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9919000267982483,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9761999845504761,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/surprise","display_name":"Surprise","score":0.976896345615387},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7695420980453491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6629803776741028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5453668236732483},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48801389336586},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4621160328388214},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4281054735183716},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4186771810054779},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3616551160812378},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.29118478298187256},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1305639147758484},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0729387104511261}],"concepts":[{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.976896345615387},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7695420980453491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6629803776741028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5453668236732483},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48801389336586},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4621160328388214},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4281054735183716},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4186771810054779},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3616551160812378},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.29118478298187256},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1305639147758484},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0729387104511261},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tnnls.2021.3105140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3105140","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34437073","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34437073","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:1910.14351","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14351","pdf_url":"https://arxiv.org/pdf/1910.14351","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:2982333597","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.14351","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.1910.14351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.14351","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.14351","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14351","pdf_url":"https://arxiv.org/pdf/1910.14351","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":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310371","display_name":"University of Otago","ror":"https://ror.org/01jmxt844"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982333597.pdf","grobid_xml":"https://content.openalex.org/works/W2982333597.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W592386890","https://openalex.org/W779494576","https://openalex.org/W1515851193","https://openalex.org/W1550989509","https://openalex.org/W1663973292","https://openalex.org/W1771410628","https://openalex.org/W1863227302","https://openalex.org/W2019515298","https://openalex.org/W2047229728","https://openalex.org/W2085754318","https://openalex.org/W2100805904","https://openalex.org/W2108677974","https://openalex.org/W2115629999","https://openalex.org/W2116459397","https://openalex.org/W2120889539","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2155806188","https://openalex.org/W2160589914","https://openalex.org/W2170610624","https://openalex.org/W2419756288","https://openalex.org/W2593766708","https://openalex.org/W2594624031","https://openalex.org/W2614839826","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2794613614","https://openalex.org/W2885550588","https://openalex.org/W2904652277","https://openalex.org/W2949608212","https://openalex.org/W2951266961","https://openalex.org/W2962730405","https://openalex.org/W2963160877","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963641140","https://openalex.org/W3004732066","https://openalex.org/W4212883601","https://openalex.org/W4214717370","https://openalex.org/W6618476874","https://openalex.org/W6638018090","https://openalex.org/W6638836233","https://openalex.org/W6660504773","https://openalex.org/W6675415620","https://openalex.org/W6683036876","https://openalex.org/W6704571135","https://openalex.org/W6716474083","https://openalex.org/W6734097942","https://openalex.org/W6734239091","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6748519856","https://openalex.org/W6753925943","https://openalex.org/W6758366860","https://openalex.org/W6759776074","https://openalex.org/W6764214684","https://openalex.org/W6764993893"],"related_works":["https://openalex.org/W2514775068","https://openalex.org/W3092804041","https://openalex.org/W2558251412","https://openalex.org/W2952767358","https://openalex.org/W3190671243","https://openalex.org/W3182043095","https://openalex.org/W3020277389","https://openalex.org/W3130078059","https://openalex.org/W2112422203","https://openalex.org/W2996251520","https://openalex.org/W2756826236","https://openalex.org/W3204861714","https://openalex.org/W3089491416","https://openalex.org/W3092213025","https://openalex.org/W2936107880","https://openalex.org/W3127131455","https://openalex.org/W3199291429","https://openalex.org/W2996148148","https://openalex.org/W2107222090","https://openalex.org/W2962854145"],"abstract_inverted_index":{"Exploration":[0],"in":[1,13,88],"environments":[2],"with":[3],"continuous":[4,89],"control":[5,90],"and":[6,25,45,68,82],"sparse":[7,91],"rewards":[8],"remains":[9],"a":[10,40,57,62],"key":[11],"challenge":[12],"reinforcement":[14],"learning":[15],"(RL).":[16],"One":[17],"of":[18,43,64,78],"the":[19,36,65,76,79],"approaches":[20],"to":[21],"encourage":[22],"more":[23],"systematic":[24],"efficient":[26],"exploration":[27,53,98],"relies":[28],"on":[29],"surprise":[30,44,52],"as":[31,61],"an":[32],"intrinsic":[33],"reward":[34,92],"for":[35],"agent.":[37],"We":[38],"introduce":[39],"new":[41],"definition":[42],"its":[46],"RL":[47],"implementation":[48],"named":[49],"variational":[50,72],"assorted":[51],"(VASE).":[54],"VASE":[55,94],"uses":[56],"Bayesian":[58],"neural":[59],"network":[60],"model":[63,81],"environment":[66],"dynamics":[67],"is":[69],"trained":[70],"using":[71],"inference,":[73],"alternately":[74],"updating":[75],"accuracy":[77],"agent's":[80],"policy.":[83],"Our":[84],"experiments":[85],"show":[86],"that":[87],"environments,":[93],"outperforms":[95],"other":[96],"surprise-based":[97],"techniques.":[99]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}