{"id":"https://openalex.org/W3193962195","doi":"https://doi.org/10.1109/icdl49984.2021.9515647","title":"Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environments","display_name":"Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environments","publication_year":2021,"publication_date":"2021-08-20","ids":{"openalex":"https://openalex.org/W3193962195","doi":"https://doi.org/10.1109/icdl49984.2021.9515647","mag":"3193962195"},"language":"en","primary_location":{"id":"doi:10.1109/icdl49984.2021.9515647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl49984.2021.9515647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-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/A5076184117","display_name":"Francesco Massari","orcid":null},"institutions":[{"id":"https://openalex.org/I118020396","display_name":"Swarthmore College","ror":"https://ror.org/012dg8a96","country_code":"US","type":"education","lineage":["https://openalex.org/I118020396"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Francesco Massari","raw_affiliation_strings":["Swarthmore College, Swarthmore, USA"],"affiliations":[{"raw_affiliation_string":"Swarthmore College, Swarthmore, USA","institution_ids":["https://openalex.org/I118020396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068164344","display_name":"Martin Biehl","orcid":"https://orcid.org/0000-0002-1670-6855"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Martin Biehl","raw_affiliation_strings":["Araya Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Araya Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I68926175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038789848","display_name":"Lisa Meeden","orcid":null},"institutions":[{"id":"https://openalex.org/I118020396","display_name":"Swarthmore College","ror":"https://ror.org/012dg8a96","country_code":"US","type":"education","lineage":["https://openalex.org/I118020396"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa Meeden","raw_affiliation_strings":["Swarthmore College, Swarthmore, USA"],"affiliations":[{"raw_affiliation_string":"Swarthmore College, Swarthmore, USA","institution_ids":["https://openalex.org/I118020396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049957600","display_name":"Ryota Kanai","orcid":"https://orcid.org/0000-0002-0186-2687"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Kanai","raw_affiliation_strings":["Araya Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Araya Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I68926175"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076184117"],"corresponding_institution_ids":["https://openalex.org/I118020396"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1116469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9763000011444092,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7424096465110779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.582287609577179},{"id":"https://openalex.org/keywords/empowerment","display_name":"Empowerment","score":0.5777221918106079},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5060243010520935},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5030671954154968},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4997265338897705},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44580379128456116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44053226709365845},{"id":"https://openalex.org/keywords/countermeasure","display_name":"Countermeasure","score":0.4372827410697937},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.43157529830932617},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2174738347530365},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1657538115978241},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11539047956466675},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11101546883583069}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7424096465110779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582287609577179},{"id":"https://openalex.org/C20555606","wikidata":"https://www.wikidata.org/wiki/Q868575","display_name":"Empowerment","level":2,"score":0.5777221918106079},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5060243010520935},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5030671954154968},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4997265338897705},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44580379128456116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44053226709365845},{"id":"https://openalex.org/C21593369","wikidata":"https://www.wikidata.org/wiki/Q1032176","display_name":"Countermeasure","level":2,"score":0.4372827410697937},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.43157529830932617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2174738347530365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1657538115978241},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11539047956466675},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11101546883583069},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl49984.2021.9515647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl49984.2021.9515647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313676","display_name":"Swarthmore College","ror":"https://ror.org/012dg8a96"},{"id":"https://openalex.org/F4320327239","display_name":"Templeton World Charity Foundation","ror":"https://ror.org/00x0z1472"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1591713425","https://openalex.org/W1786044565","https://openalex.org/W1863227302","https://openalex.org/W1917036087","https://openalex.org/W1959608418","https://openalex.org/W2000514530","https://openalex.org/W2034806191","https://openalex.org/W2120889539","https://openalex.org/W2556477470","https://openalex.org/W2557579533","https://openalex.org/W2808420305","https://openalex.org/W2899205164","https://openalex.org/W2945568361","https://openalex.org/W2954142106","https://openalex.org/W2962730405","https://openalex.org/W2963438456","https://openalex.org/W2964067469","https://openalex.org/W2992753615","https://openalex.org/W4288289109","https://openalex.org/W4293469690","https://openalex.org/W4299502902","https://openalex.org/W6640963894","https://openalex.org/W6650587873","https://openalex.org/W6660504773","https://openalex.org/W6685757253","https://openalex.org/W6729906282","https://openalex.org/W6730153900","https://openalex.org/W6748603076","https://openalex.org/W6756303580","https://openalex.org/W6762304338","https://openalex.org/W6764724164","https://openalex.org/W6770945675"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W2366629217"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"is":[3,18],"known":[4],"to":[5,19,57,83,122,144,146,158,166],"be":[6,164],"often":[7],"unsuccessful":[8],"in":[9,129],"environments":[10],"with":[11,23,98],"sparse":[12,131],"extrinsic":[13],"rewards.":[14,152],"A":[15],"possible":[16],"countermeasure":[17],"endow":[20],"RL":[21],"agents":[22,121],"an":[24,89,125],"intrinsic":[25,45,151],"reward":[26,46,132],"function,":[27],"or":[28],"\u2018intrinsic":[29],"motivation\u2019,":[30],"which":[31,80],"rewards":[32,55],"the":[33,40,50,58,62,85,103,106,117,136,159],"agent":[34,63,138],"based":[35,48],"on":[36,49,73],"certain":[37],"features":[38],"of":[39,52,60,119,124],"current":[41],"sensor":[42,95,108],"state.":[43],"An":[44],"function":[47],"principle":[51],"empowerment":[53,137,162],"assigns":[54],"proportional":[56],"amount":[59],"control":[61],"has":[64],"over":[65],"its":[66,140],"own":[67],"sensors.":[68],"We":[69,115],"implemented":[70],"a":[71,74,99,111],"variation":[72],"recently":[75],"proposed":[76],"intrinsically":[77],"motivated":[78],"agent,":[79,87],"we":[81],"refer":[82],"as":[84],"\u2018curious\u2019":[86],"and":[88,139],"empowerment-inspired":[90],"agent.":[91],"The":[92],"former":[93],"leverages":[94],"state":[96,109],"encoding":[97],"variational":[100,112],"autoencoder,":[101],"while":[102],"latter":[104],"predicts":[105],"next":[107],"via":[110],"information":[113],"bottleneck.":[114],"compared":[116],"performance":[118],"both":[120],"that":[123,161],"advantage":[126],"actor-critic":[127],"baseline":[128],"four":[130],"grid":[133],"worlds.":[134],"Both":[135],"curious":[141],"competitor":[142],"seem":[143],"benefit":[145],"similar":[147],"extents":[148],"from":[149],"their":[150],"This":[153],"provides":[154],"some":[155],"experimental":[156],"support":[157],"conjecture":[160],"can":[163],"used":[165],"drive":[167],"exploration.":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}