{"id":"https://openalex.org/W2998825830","doi":"https://doi.org/10.1109/taai48200.2019.8959896","title":"Deep Residual Attention Reinforcement Learning","display_name":"Deep Residual Attention Reinforcement Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2998825830","doi":"https://doi.org/10.1109/taai48200.2019.8959896","mag":"2998825830"},"language":"en","primary_location":{"id":"doi:10.1109/taai48200.2019.8959896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taai48200.2019.8959896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Technologies and Applications of Arti\ufb01cial Intelligence (TAAI)","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/A5112318879","display_name":"Hanhua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hanhua Zhu","raw_affiliation_strings":["Graduate School of Interdisciplinary Information Studies, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Interdisciplinary Information Studies, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103172324","display_name":"Tomoyuki Kaneko","orcid":"https://orcid.org/0000-0001-8051-2388"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyuki Kaneko","raw_affiliation_strings":["Interfaculty in Information Studies, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Interfaculty in Information Studies, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112318879"],"corresponding_institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67468867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"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":0.9994999766349792,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9879999756813049,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9871000051498413,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8901007175445557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7786598205566406},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6286227107048035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536336362361908},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.526589572429657},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5200093388557434},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3396541476249695},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0962485671043396}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8901007175445557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786598205566406},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6286227107048035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536336362361908},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.526589572429657},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5200093388557434},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3396541476249695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0962485671043396},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taai48200.2019.8959896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taai48200.2019.8959896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Technologies and Applications of Arti\ufb01cial Intelligence (TAAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W2145339207","https://openalex.org/W2147527908","https://openalex.org/W2194775991","https://openalex.org/W2195446438","https://openalex.org/W2577645110","https://openalex.org/W2786036274","https://openalex.org/W2807340089","https://openalex.org/W2894976951","https://openalex.org/W2899742573","https://openalex.org/W2914831223","https://openalex.org/W2951527505","https://openalex.org/W2962858109","https://openalex.org/W2962966033","https://openalex.org/W2963403868","https://openalex.org/W2963495494","https://openalex.org/W2964043796","https://openalex.org/W2978184346","https://openalex.org/W3037207827","https://openalex.org/W4297797010","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6682137061","https://openalex.org/W6687590523","https://openalex.org/W6692846177","https://openalex.org/W6739901393","https://openalex.org/W6748638692","https://openalex.org/W6752216966","https://openalex.org/W6755069753","https://openalex.org/W6755494043"],"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":{"Making":[0],"decisions":[1],"based":[2],"more":[3,69],"on":[4,104],"the":[5,13,34,45,49,75,80,85,89,97,105,111],"crucial":[6,50,106],"objects":[7,51,71,107],"which":[8,67],"are":[9],"closely":[10],"connected":[11],"to":[12,43,84],"reward":[14],"in":[15,22,61,79],"a":[16],"given":[17],"visual":[18],"input":[19],"is":[20],"advantageous":[21],"reinforcement":[23],"learning.":[24],"In":[25],"this":[26],"work,":[27],"we":[28],"incorporate":[29],"an":[30],"attention-based":[31],"structure":[32,36],"into":[33],"network":[35],"of":[37,77,91,113],"Importance":[38],"Weighted":[39],"Actor-Learner":[40],"Architecture":[41],"(IMPALA)":[42],"help":[44],"model":[46],"find":[47],"out":[48],"and":[52,64,108],"propose":[53],"Deep":[54],"Residual":[55],"Attention":[56],"Reinforcement":[57],"Learning":[58],"(DRARL).":[59],"Experiments":[60],"Atari":[62],"games":[63],"special":[65],"environments":[66],"have":[68],"irrelevant":[70],"than":[72],"usual":[73],"demonstrate":[74],"superiority":[76],"DRARL":[78],"multi-objects":[81],"environment":[82],"compared":[83],"original":[86],"IMPALA.":[87,114],"Furthermore,":[88],"visualization":[90],"trained":[92],"agents'":[93],"attention":[94,99],"indicates":[95],"that":[96],"additional":[98],"mechanism":[100],"helps":[101],"IMPALA":[102],"concentrate":[103],"therefore":[109],"improves":[110],"performance":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}