{"id":"https://openalex.org/W7105666233","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227762","title":"Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning","display_name":"Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105666233","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227762"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.manchester.ac.uk/en/publications/8792966c-c9ba-4456-9557-f004424c64fc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tien Pham","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tien Pham","raw_affiliation_strings":["The University of Manchester,School of Computer Science,Manchester,UK"],"affiliations":[{"raw_affiliation_string":"The University of Manchester,School of Computer Science,Manchester,UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":null,"display_name":"Angelo Cangelosi","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Angelo Cangelosi","raw_affiliation_strings":["The University of Manchester,School of Computer Science,Manchester,UK"],"affiliations":[{"raw_affiliation_string":"The University of Manchester,School of Computer Science,Manchester,UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93235125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9153000116348267,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9153000116348267,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.02710000053048134,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.013399999588727951,"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/feature","display_name":"Feature (linguistics)","score":0.677299976348877},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6729000210762024},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6114000082015991},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.571399986743927},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.541100025177002},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.438400000333786},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4318000078201294},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43050000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7415000200271606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.677299976348877},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43959999084472656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.39800000190734863},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/8792966c-c9ba-4456-9557-f004424c64fc","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/8792966c-c9ba-4456-9557-f004424c64fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pham, T & Cangelosi, A 2025, Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning. in IJCNN2025 International Joint Conference on Neural Networks. https://doi.org/10.1109/ijcnn64981.2025.11227762","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/8792966c-c9ba-4456-9557-f004424c64fc","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/8792966c-c9ba-4456-9557-f004424c64fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pham, T & Cangelosi, A 2025, Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning. in IJCNN2025 International Joint Conference on Neural Networks. https://doi.org/10.1109/ijcnn64981.2025.11227762","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2740388348","https://openalex.org/W2761873684","https://openalex.org/W2951360122","https://openalex.org/W2953461088","https://openalex.org/W3004058922","https://openalex.org/W3034514369","https://openalex.org/W3098338892","https://openalex.org/W3159481202","https://openalex.org/W4289752563","https://openalex.org/W4385245566","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"Current":[0],"approaches":[1],"in":[2,9,20,60,120,130],"Explainable":[3],"Deep":[4],"Reinforcement":[5],"Learning":[6],"have":[7],"limitations":[8],"which":[10],"the":[11,18,37,56,61,86,95,106,140,154,157,169,176,179],"attention":[12,48,76,111],"mask":[13,49,112],"has":[14],"a":[15,26,67,73],"displacement":[16],"with":[17],"objects":[19,127],"visual":[21,131],"input.":[22,132],"This":[23],"work":[24],"addresses":[25],"spatial":[27,62,121],"problem":[28],"within":[29],"traditional":[30],"Convolutional":[31],"Neural":[32],"Networks":[33],"(CNNs).":[34],"We":[35],"propose":[36],"Interpretable":[38,96,134],"Feature":[39,97,135],"Extractor":[40,98,136],"(IFE)":[41],"architecture,":[42],"aimed":[43],"at":[44],"generating":[45],"an":[46,80],"accurate":[47,119],"to":[50,71,84,104,152],"illustrate":[51],"both":[52],"\"what\"":[53],"and":[54,123,142,146,164],"\"where\"":[55],"agent":[57],"concentrates":[58],"on":[59,148,160],"domain.":[63],"Our":[64],"design":[65],"incorporates":[66],"Human-Understandable":[68],"Encoding":[69,82],"module":[70,83],"generate":[72],"fully":[74],"interpretable":[75],"mask,":[77],"followed":[78],"by":[79,117,174],"Agent-Friendly":[81],"enhance":[85],"agent\u2019s":[87],"learning":[88,103],"efficiency.":[89],"These":[90],"two":[91],"components":[92],"together":[93],"form":[94],"for":[99],"vision-based":[100],"deep":[101],"reinforcement":[102],"enable":[105],"model\u2019s":[107],"interpretability.":[108],"The":[109,133],"resulting":[110],"is":[113,137],"consistent,":[114],"highly":[115],"understandable":[116],"humans,":[118],"dimension,":[122],"effectively":[124],"highlights":[125],"important":[126],"or":[128],"locations":[129],"integrated":[138],"into":[139,178],"Fast":[141],"Data-efficient":[143],"Rainbow":[144],"framework,":[145],"evaluated":[147],"57":[149],"ATARI":[150],"games":[151],"show":[153],"effectiveness":[155],"of":[156,171],"proposed":[158],"approach":[159,173],"Spatial":[161],"Preservation,":[162],"Interpretability,":[163],"Data-efficiency.":[165],"Finally,":[166],"we":[167],"showcase":[168],"versatility":[170],"our":[172],"incorporating":[175],"IFE":[177],"Asynchronous":[180],"Advantage":[181],"Actor-Critic":[182],"Model.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}