{"id":"https://openalex.org/W2033551142","doi":"https://doi.org/10.1109/tamd.2015.2419715","title":"Action Priors for Learning Domain Invariances","display_name":"Action Priors for Learning Domain Invariances","publication_year":2015,"publication_date":"2015-04-03","ids":{"openalex":"https://openalex.org/W2033551142","doi":"https://doi.org/10.1109/tamd.2015.2419715","mag":"2033551142"},"language":"en","primary_location":{"id":"doi:10.1109/tamd.2015.2419715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tamd.2015.2419715","pdf_url":null,"source":{"id":"https://openalex.org/S108448409","display_name":"IEEE Transactions on Autonomous Mental Development","issn_l":"1943-0604","issn":["1943-0604","1943-0612"],"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 Autonomous Mental Development","raw_type":"journal-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/A5068297734","display_name":"Benjamin Rosman","orcid":"https://orcid.org/0000-0002-0284-4114"},"institutions":[{"id":"https://openalex.org/I21360634","display_name":"Council for Scientific and Industrial Research","ror":"https://ror.org/05j00sr48","country_code":"ZA","type":"government","lineage":["https://openalex.org/I21360634"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Benjamin Rosman","raw_affiliation_strings":["Mobile Intelligent Autonomous Systems, Council for Scientific and Industrial Research (CSIR), South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Intelligent Autonomous Systems, Council for Scientific and Industrial Research (CSIR), South Africa","institution_ids":["https://openalex.org/I21360634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071122608","display_name":"Subramanian Ramamoorthy","orcid":"https://orcid.org/0000-0002-6300-5103"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Subramanian Ramamoorthy","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK","Sch. of Informatics, Univ. of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Sch. of Informatics, Univ. of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.04767747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":"2","first_page":"107","last_page":"118"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.991100013256073,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9832000136375427,"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/prior-probability","display_name":"Prior probability","score":0.8478452563285828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6829337477684021},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6171497106552124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6140819191932678},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5548202991485596},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5443817973136902},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5140570402145386},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4566551446914673},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4118099510669708},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25794392824172974},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2127830982208252},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.09930986166000366},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0782279372215271}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8478452563285828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6829337477684021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6171497106552124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6140819191932678},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5548202991485596},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5443817973136902},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5140570402145386},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4566551446914673},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4118099510669708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25794392824172974},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2127830982208252},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.09930986166000366},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0782279372215271},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tamd.2015.2419715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tamd.2015.2419715","pdf_url":null,"source":{"id":"https://openalex.org/S108448409","display_name":"IEEE Transactions on Autonomous Mental Development","issn_l":"1943-0604","issn":["1943-0604","1943-0612"],"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 Autonomous Mental Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W29099680","https://openalex.org/W32403112","https://openalex.org/W172293765","https://openalex.org/W1586944634","https://openalex.org/W1598748993","https://openalex.org/W1600813180","https://openalex.org/W1612195517","https://openalex.org/W1933657216","https://openalex.org/W1970828375","https://openalex.org/W2030892052","https://openalex.org/W2031727428","https://openalex.org/W2032465344","https://openalex.org/W2059569317","https://openalex.org/W2079247031","https://openalex.org/W2084760838","https://openalex.org/W2091394515","https://openalex.org/W2091938290","https://openalex.org/W2097381042","https://openalex.org/W2102495692","https://openalex.org/W2118022839","https://openalex.org/W2121863487","https://openalex.org/W2133013156","https://openalex.org/W2149390907","https://openalex.org/W2165792602","https://openalex.org/W2166254514","https://openalex.org/W2166367303","https://openalex.org/W2168359464","https://openalex.org/W2245825236","https://openalex.org/W2269160106","https://openalex.org/W2519876750","https://openalex.org/W2527422040","https://openalex.org/W2550648340","https://openalex.org/W2732054432","https://openalex.org/W2992130099","https://openalex.org/W4214717370","https://openalex.org/W4229687485","https://openalex.org/W6601161420","https://openalex.org/W6635131279","https://openalex.org/W6636553048","https://openalex.org/W6674600207","https://openalex.org/W6677738694","https://openalex.org/W6679564466","https://openalex.org/W6684428122","https://openalex.org/W6684499351","https://openalex.org/W6690740874","https://openalex.org/W6693697903"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W1965695708","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576","https://openalex.org/W2108112111","https://openalex.org/W2060421996"],"abstract_inverted_index":{"An":[0],"agent":[1],"tasked":[2],"with":[3,154,200],"solving":[4,66],"a":[5,21,95,169,174],"number":[6],"of":[7,60,65,97,107,118,125,133,158],"different":[8,32],"decision":[9],"making":[10],"problems":[11],"in":[12,39,48,104,166,168,184],"similar":[13],"environments":[14],"has":[15,57],"an":[16],"opportunity":[17],"to":[18,31,45,52,110],"learn":[19],"over":[20,79,142],"longer":[22],"timescale":[23],"than":[24,146],"each":[25],"individual":[26],"task.":[27],"Through":[28],"examining":[29],"solutions":[30],"tasks,":[33],"it":[34],"can":[35,91],"uncover":[36],"behavioral":[37],"invariances":[38],"the":[40,58,63,80,105,126,131,155],"domain,":[41,178],"by":[42],"identifying":[43],"actions":[44],"be":[46,92],"prioritized":[47],"local":[49],"contexts,":[50],"invariant":[51],"task":[53],"details.":[54],"This":[55],"information":[56],"effect":[59],"greatly":[61],"increasing":[62],"speed":[64,182],"new":[67,186],"problems.":[68],"We":[69,100,137],"formalise":[70],"this":[71,192],"notion":[72],"as":[73,77],"action":[74,81,102,112,119,140],"priors,":[75],"defined":[76],"distributions":[78],"space,":[82],"conditioned":[83],"on":[84],"environment":[85,172],"state,":[86],"and":[87,152,173,179,197],"show":[88,180],"how":[89],"these":[90],"learnt":[93],"from":[94,202],"set":[96],"value":[98],"functions.":[99],"apply":[101],"priors":[103,120,141,163],"setting":[106],"reinforcement":[108],"learning,":[109],"bias":[111],"selection":[113],"during":[114,135],"exploration.":[115],"Aggressive":[116],"use":[117],"performs":[121],"context":[122],"based":[123],"pruning":[124],"available":[127],"actions,":[128],"thus":[129],"reducing":[130],"complexity":[132],"lookahead":[134],"search.":[136],"additionally":[138],"define":[139],"observation":[143],"features,":[144],"rather":[145],"states,":[147],"which":[148],"provides":[149],"further":[150],"flexibility":[151],"generalizability,":[153],"additional":[156],"benefit":[157],"enabling":[159],"feature":[160],"selection.":[161],"Action":[162],"are":[164],"demonstrated":[165],"experiments":[167],"simulated":[170],"factory":[171],"large":[175],"random":[176],"graph":[177],"significant":[181],"ups":[183],"learning":[185],"tasks.":[187],"Furthermore,":[188],"we":[189],"argue":[190],"that":[191],"mechanism":[193],"is":[194,198],"cognitively":[195],"plausible,":[196],"compatible":[199],"findings":[201],"cognitive":[203],"psychology.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}