{"id":"https://openalex.org/W2989957090","doi":"https://doi.org/10.3233/faia190111","title":"Speeding up Reinforcement Learning by Combining Attention and Agency Features","display_name":"Speeding up Reinforcement Learning by Combining Attention and Agency Features","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989957090","doi":"https://doi.org/10.3233/faia190111","mag":"2989957090"},"language":"en","primary_location":{"id":"doi:10.3233/faia190111","is_oa":false,"landing_page_url":"https://doi.org/10.3233/faia190111","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.12623","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116360545","display_name":"Demirel Berkay","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Demirel Berkay","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113693967","display_name":"Sarah Marti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e1nchez-Fibla Mart\u00ed","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5116360545"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2759,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60363552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T10581","display_name":"Neural dynamics and brain function","score":0.9860000014305115,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9860000014305115,"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/agency","display_name":"Agency (philosophy)","score":0.6702452301979065},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6277076601982117},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5756553411483765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42182183265686035},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3956683576107025},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.38233333826065063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3275420665740967},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12114217877388},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11704772710800171},{"id":"https://openalex.org/keywords/social-science","display_name":"Social science","score":0.0378270149230957}],"concepts":[{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.6702452301979065},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6277076601982117},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5756553411483765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42182183265686035},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3956683576107025},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38233333826065063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3275420665740967},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12114217877388},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11704772710800171},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0378270149230957}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia190111","is_oa":false,"landing_page_url":"https://doi.org/10.3233/faia190111","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1912.12623","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.12623","pdf_url":"https://arxiv.org/pdf/1912.12623","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.12623","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.12623","pdf_url":"https://arxiv.org/pdf/1912.12623","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1581202840","https://openalex.org/W1901972595","https://openalex.org/W2145339207","https://openalex.org/W2186143850","https://openalex.org/W2604626881","https://openalex.org/W2743339080","https://openalex.org/W2767929917","https://openalex.org/W2788058077","https://openalex.org/W2950892788","https://openalex.org/W2951527505","https://openalex.org/W2954984794","https://openalex.org/W4295246696"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"When":[0],"playing":[1],"video-games":[2],"we":[3,8,11],"immediately":[4],"detect":[5],"which":[6,107],"entity":[7],"control":[9],"and":[10,21,78,103,123,130,138],"center":[12],"the":[13,19,47,53,58,62,73,76,89,97,136,143,158,164],"attention":[14,102],"towards":[15],"it":[16],"to":[17,31,61,82,118,168],"focus":[18],"learning":[20,48],"reduce":[22],"its":[23,67],"dimensionality.":[24],"Reinforcement":[25],"Learning":[26],"(RL)":[27],"has":[28],"been":[29,110],"able":[30],"deal":[32],"with":[33],"big":[34],"state":[35,60,77,99,137,152,165],"spaces,":[36],"including":[37,127,140],"states":[38],"derived":[39],"from":[40,57],"pixel":[41],"images":[42],"in":[43,113],"Atari":[44],"games,":[45],"but":[46,115],"is":[49,69],"slow,":[50],"depends":[51],"on":[52],"brute":[54],"force":[55],"mapping":[56],"global":[59,129,159],"action":[63],"values":[64],"(Q-function),":[65],"thus":[66],"performance":[68],"severely":[70],"affected":[71],"by":[72],"dimensionality":[74],"of":[75,88,96,135,142,163],"cannot":[79],"be":[80],"transferred":[81],"other":[83,86],"games":[84],"or":[85],"parts":[87],"same":[90],"game.":[91],"We":[92,121],"propose":[93,122],"different":[94,125],"transformations":[95],"input":[98],"that":[100,147],"combine":[101],"agency":[104,132],"detection":[105],"mechanisms":[106],"both":[108,128],"have":[109],"addressed":[111],"separately":[112],"RL":[114],"not":[116],"together":[117],"our":[119],"knowledge.":[120],"benchmark":[124],"architectures":[126],"local":[131],"centered":[133],"versions":[134,162],"also":[139],"summaries":[141],"surroundings.":[144],"Results":[145],"suggest":[146],"even":[148],"a":[149],"redundant":[150],"global-local":[151],"network":[153],"can":[154],"learn":[155],"faster":[156],"than":[157],"alone.":[160],"Summarized":[161],"look":[166],"promising":[167],"achieve":[169],"input-size":[170],"independence":[171],"learning.":[172]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-12-05T00:00:00"}