{"id":"https://openalex.org/W7161841375","doi":"https://doi.org/10.1109/icarsc70216.2026.11523309","title":"Techniques to Improve Attention-based Deep Reinforcement Learning in Vision-based Domains","display_name":"Techniques to Improve Attention-based Deep Reinforcement Learning in Vision-based Domains","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7161841375","doi":"https://doi.org/10.1109/icarsc70216.2026.11523309"},"language":null,"primary_location":{"id":"doi:10.1109/icarsc70216.2026.11523309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarsc70216.2026.11523309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5034695462","display_name":"Fernando Duarte","orcid":"https://orcid.org/0000-0002-9503-9084"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Fernando Fradique Duarte","raw_affiliation_strings":["University of Aveiro,IEETA, DETI, LASI,Aveiro,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aveiro,IEETA, DETI, LASI,Aveiro,Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055569781","display_name":"Nuno Lau","orcid":"https://orcid.org/0000-0003-0513-158X"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Lau","raw_affiliation_strings":["University of Aveiro,IEETA, DETI, LASI,Aveiro,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aveiro,IEETA, DETI, LASI,Aveiro,Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062824074","display_name":"Artur Pereira","orcid":"https://orcid.org/0000-0002-7099-1247"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Artur Pereira","raw_affiliation_strings":["University of Aveiro,IEETA, DETI, LASI,Aveiro,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aveiro,IEETA, DETI, LASI,Aveiro,Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135106309","display_name":"Lu\u00eds Paulo Reis","orcid":null},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Lu\u00eds Paulo Reis","raw_affiliation_strings":["University of Porto,Faculty of Engineering,Department of Informatics Engineering,Porto,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto,Faculty of Engineering,Department of Informatics Engineering,Porto,Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"21","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2671000063419342,"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":0.2671000063419342,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.04650000110268593,"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/T11094","display_name":"Face Recognition and Perception","score":0.04540000110864639,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.4431000053882599},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3158000111579895},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3001999855041504},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.29670000076293945},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2946999967098236},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28439998626708984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5591999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5322999954223633},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2680000066757202},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarsc70216.2026.11523309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarsc70216.2026.11523309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46161162853240967,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330374","display_name":"Foundation for Science and Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W4293363567","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"Attention-based":[0],"techniques":[1,50,74,137,148],"are":[2,106,126],"amongst":[3],"the":[4,9,14,21,46,59,66,77,87,94,99,103,117,123,133,136,167,183],"many":[5],"contributing":[6],"factors":[7],"to":[8,53,56,75,108,131,158,178],"rapid":[10],"advancements":[11],"achieved":[12],"in":[13,20,86,160,166],"field":[15,168],"of":[16,33,43,48,79,89,102,116,119,135,169],"Artificial":[17],"Intelligence":[18],"research":[19],"last":[22],"decades.":[23],"In":[24],"fact,":[25],"attention-based":[26,49,80,154],"agents":[27,105],"have":[28],"found":[29],"a":[30,161],"wide":[31],"range":[32],"applicability.":[34],"Vision-based":[35],"Deep":[36,81],"Reinforcement":[37,82],"Learning":[38,83],"is":[39],"one":[40],"such":[41,164],"area":[42],"application,":[44],"where":[45],"use":[47],"has":[51,157],"proven":[52],"be":[54,150],"essential":[55],"improve":[57,76],"both":[58],"agent\u2019s":[60],"performance":[61,78,111],"and":[62,129,180],"interpretability.":[63],"Inspired":[64],"by":[65],"Top-Down":[67],"Attention":[68],"architecture,":[69],"this":[70,140],"work":[71,141],"presents":[72],"four":[73],"agents,":[84],"specifically":[85,143],"scope":[88],"vision-based":[90,162],"domains.":[91],"Interestingly,":[92],"using":[93],"same":[95],"underlying":[96],"architecture":[97],"as":[98,165],"baseline,":[100],"some":[101],"resulting":[104],"able":[107],"achieve":[109],"higher":[110],"while":[112],"requiring":[113],"only":[114],"half":[115],"number":[118],"trainable":[120],"parameters.":[121],"Overall,":[122],"results":[124],"obtained":[125],"very":[127],"promising":[128],"seem":[130],"validate":[132,181],"suitability":[134],"proposed.":[138],"While":[139],"focuses":[142],"on":[144],"video":[145],"games,":[146],"these":[147],"may":[149],"used":[151,177],"with":[152],"any":[153],"agent":[155],"that":[156],"operate":[159],"domain,":[163],"robotics.":[170],"The":[171],"Atari":[172],"2600":[173],"videogame":[174],"benchmark":[175],"was":[176],"perform":[179],"all":[182],"experiments.":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-21T00:00:00"}