{"id":"https://openalex.org/W3132298418","doi":null,"title":"Escaping Stochastic Traps with Aleatoric Mapping Agents.","display_name":"Escaping Stochastic Traps with Aleatoric Mapping Agents.","publication_year":2021,"publication_date":"2021-02-08","ids":{"openalex":"https://openalex.org/W3132298418","mag":"3132298418"},"language":"en","primary_location":{"id":"mag:3132298418","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.04399.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.04399.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026671424","display_name":"Augustine N. Mavor-Parker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Augustine N. Mavor-Parker","raw_affiliation_strings":["University College London\u2020"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London\u2020","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kimberly A. Young","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kimberly A. Young","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086282819","display_name":"Caswell Barry","orcid":"https://orcid.org/0000-0001-6718-0649","observed_orcids":["https://orcid.org/0000-0001-6718-0649"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caswell Barry","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6718-0649","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056135069","display_name":"Lewis D. Griffin","orcid":"https://orcid.org/0000-0001-6286-2018","observed_orcids":["https://orcid.org/0000-0001-6286-2018"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lewis D. Griffin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6286-2018","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":9.999999747378752e-05,"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/T11883","display_name":"Embodied and Extended Cognition","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity-driven-learning","display_name":"curiosity-driven learning","score":0.9330000281333923},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.7400000095367432},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.7049999833106995},{"id":"https://openalex.org/keywords/aleatoric-uncertainty","display_name":"aleatoric uncertainty","score":0.7910000085830688},{"id":"https://openalex.org/keywords/cholinergic-system","display_name":"cholinergic system","score":0.7850000262260437},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8873698115348816},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.683468759059906},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6222813129425049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5869603157043457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47236043214797974},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43614310026168823},{"id":"https://openalex.org/C177605951","wikidata":"https://www.wikidata.org/wiki/Q1484503","display_name":"Herding","level":2,"score":0.43518829345703125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4089708924293518},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2668505311012268},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.2224419116973877},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15196746587753296},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10428890585899353},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09456092119216919},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C97137747","wikidata":"https://www.wikidata.org/wiki/Q38112","display_name":"Forestry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3132298418","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.04399.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:3132298418","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.04399.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1600050350","https://openalex.org/W1663973292","https://openalex.org/W1901129140","https://openalex.org/W1977106703","https://openalex.org/W1988526405","https://openalex.org/W1998127479","https://openalex.org/W2020920737","https://openalex.org/W2044129724","https://openalex.org/W2053696585","https://openalex.org/W2060198709","https://openalex.org/W2073384958","https://openalex.org/W2101491694","https://openalex.org/W2104615036","https://openalex.org/W2108393070","https://openalex.org/W2116737087","https://openalex.org/W2121863487","https://openalex.org/W2130152984","https://openalex.org/W2150468603","https://openalex.org/W2154562678","https://openalex.org/W2260756217","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2560321925","https://openalex.org/W2600383743","https://openalex.org/W2736601468","https://openalex.org/W2751973545","https://openalex.org/W2754879180","https://openalex.org/W2769704218","https://openalex.org/W2788755844","https://openalex.org/W2796979132","https://openalex.org/W2885550588","https://openalex.org/W2903158431","https://openalex.org/W2945850646","https://openalex.org/W2948199691","https://openalex.org/W2950718433","https://openalex.org/W2962730405","https://openalex.org/W2963276097","https://openalex.org/W2963820385","https://openalex.org/W2964067469","https://openalex.org/W2964121744","https://openalex.org/W2980423179","https://openalex.org/W2996110979","https://openalex.org/W2996695841","https://openalex.org/W3014596384","https://openalex.org/W3131119906"],"related_works":["https://openalex.org/W4287330569","https://openalex.org/W4309795624","https://openalex.org/W3207362082","https://openalex.org/W4401354605","https://openalex.org/W7124295687","https://openalex.org/W2888332784","https://openalex.org/W4283800386","https://openalex.org/W4200077967","https://openalex.org/W3030973013","https://openalex.org/W1561491641"],"abstract_inverted_index":{"Exploration":[0],"in":[1,27,132],"environments":[2],"with":[3,34,105],"sparse":[4],"rewards":[5,21,101],"is":[6,83,135],"difficult":[7],"for":[8,90,102,128],"artificial":[9],"agents.":[10,125],"Curiosity":[11],"driven":[12,124],"learning":[13],"--":[14,22],"using":[15],"feed-forward":[16],"prediction":[17],"errors":[18],"as":[19],"intrinsic":[20,100],"has":[23],"achieved":[24,84],"some":[25],"success":[26],"these":[28],"scenarios,":[29],"but":[30],"fails":[31],"when":[32],"faced":[33],"action-dependent":[35,117],"noise":[36],"sources.":[37],"We":[38,109],"present":[39],"aleatoric":[40,107],"mapping":[41],"agents":[42],"(AMAs),":[43],"a":[44],"neuroscience":[45],"inspired":[46],"solution":[47],"modeled":[48],"on":[49],"the":[50,54,65,77,80,91],"cholinergic":[51],"system":[52],"of":[53,64,70,79,95],"mammalian":[55],"brain.":[56],"AMAs":[57,111],"aim":[58],"to":[59,114],"explicitly":[60],"ascertain":[61],"which":[62],"dynamics":[63,73],"environment":[66],"are":[67,74,112],"unpredictable,":[68],"regardless":[69],"whether":[71],"those":[72,103],"induced":[75],"by":[76,85],"actions":[78],"agent.":[81],"This":[82],"generating":[86],"separate":[87],"forward":[88],"predictions":[89],"mean":[92],"and":[93,98],"variance":[94],"future":[96],"states":[97],"reducing":[99],"transitions":[104],"high":[106],"variance.":[108],"show":[110],"able":[113],"effectively":[115],"circumvent":[116],"stochastic":[118],"traps":[119],"that":[120],"immobilise":[121],"conventional":[122],"curiosity":[123],"The":[126],"code":[127],"all":[129],"experiments":[130],"presented":[131],"this":[133,138],"paper":[134],"open":[136],"sourced:":[137],"http":[139],"URL.":[140]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-03-01T00:00:00"}