{"id":"https://openalex.org/W6894416521","doi":"https://doi.org/10.5555/3635637.3662926","title":"MaDi:Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","display_name":"MaDi:Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-06","ids":{"openalex":"https://openalex.org/W6894416521","doi":"https://doi.org/10.5555/3635637.3662926"},"language":"en","primary_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/a9f9c7b0-dd30-4bf2-b4e8-a6f7cd4c314b","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a9f9c7b0-dd30-4bf2-b4e8-a6f7cd4c314b","pdf_url":"https://pure.tue.nl/ws/files/351244761/3635637.3662926.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grooten, B, Taylor, M E, Tomilin, T, Mahmood, A R, Vasan, G, Fang, M, Pechenizkiy, M & Mocanu, D C 2024, MaDi : Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning. in M Dastani, J S Sichman, N Alechina & V Dignum (eds), AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), Richland, pp. 733-742, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://dl.acm.org/doi/10.5555/3635637.3662926 >","raw_type":"info:eu-repo/semantics/publishedVersion"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/351244761/3635637.3662926.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Grooten, Bram; id_orcid 0000-0001-5084-6977","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grooten, Bram; id_orcid 0000-0001-5084-6977","raw_affiliation_strings":["Eindhoven University of Technology Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Taylor, Matthew E.","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Taylor, Matthew E.","raw_affiliation_strings":["University of Alberta & Alberta Machine Intelligence Institute (Amii ) Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta & Alberta Machine Intelligence Institute (Amii ) Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tomilin, Tristan; id_orcid 0009-0009-5805-3395","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomilin, Tristan; id_orcid 0009-0009-5805-3395","raw_affiliation_strings":["Eindhoven University of Technology Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mahmood, A. Rupam","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mahmood, A. Rupam","raw_affiliation_strings":["University of Alberta & Alberta Machine Intelligence Institute (Amii ) Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta & Alberta Machine Intelligence Institute (Amii ) Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vasan, Gautham","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vasan, Gautham","raw_affiliation_strings":["University of Alberta Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fang, Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fang, Meng","raw_affiliation_strings":["University of Liverpool United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Liverpool United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pechenizkiy, Mykola; id_orcid 0000-0003-4955-0743","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088784","display_name":"ACT Foundation","ror":"https://ror.org/009qwqe18","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210088784"]},{"id":"https://openalex.org/I4210149743","display_name":"Sinai Health System","ror":"https://ror.org/05j8naw58","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210149743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pechenizkiy, Mykola; id_orcid 0000-0003-4955-0743","raw_affiliation_strings":["Eindhoven University of Technology Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Mocanu, Decebal Constantin; id_orcid 0000-0002-5636-7683","orcid":null},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Mocanu, Decebal Constantin; id_orcid 0000-0002-5636-7683","raw_affiliation_strings":["University of Luxembourg Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg Luxembourg","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30760164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4300999939441681,"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":0.4300999939441681,"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":0.179299995303154,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06629999727010727,"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/generalization","display_name":"Generalization","score":0.8094000220298767},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7892000079154968},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6861000061035156},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5465999841690063},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.49390000104904175},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4268999993801117},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4146000146865845}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8094000220298767},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7892000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659000158309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7020999789237976},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6861000061035156},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5465999841690063},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3982999920845032},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.30809998512268066},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/a9f9c7b0-dd30-4bf2-b4e8-a6f7cd4c314b","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a9f9c7b0-dd30-4bf2-b4e8-a6f7cd4c314b","pdf_url":"https://pure.tue.nl/ws/files/351244761/3635637.3662926.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grooten, B, Taylor, M E, Tomilin, T, Mahmood, A R, Vasan, G, Fang, M, Pechenizkiy, M & Mocanu, D C 2024, MaDi : Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning. in M Dastani, J S Sichman, N Alechina & V Dignum (eds), AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), Richland, pp. 733-742, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://dl.acm.org/doi/10.5555/3635637.3662926 >","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/a9f9c7b0-dd30-4bf2-b4e8-a6f7cd4c314b","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a9f9c7b0-dd30-4bf2-b4e8-a6f7cd4c314b","pdf_url":"https://pure.tue.nl/ws/files/351244761/3635637.3662926.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grooten, B, Taylor, M E, Tomilin, T, Mahmood, A R, Vasan, G, Fang, M, Pechenizkiy, M & Mocanu, D C 2024, MaDi : Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning. in M Dastani, J S Sichman, N Alechina & V Dignum (eds), AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), Richland, pp. 733-742, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://dl.acm.org/doi/10.5555/3635637.3662926 >","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6894416521.pdf","grobid_xml":"https://content.openalex.org/works/W6894416521.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"visual":[1],"world":[2],"provides":[3],"an":[4],"abundance":[5],"of":[6,79],"information,":[7],"but":[8],"many":[9],"input":[10],"pixels":[11],"received":[12],"by":[13,68,86],"agents":[14,20,83],"often":[15],"contain":[16],"distracting":[17],"stimuli.":[18],"Autonomous":[19],"need":[21],"the":[22,69,75,91,103,115,121,126,139,156],"ability":[23],"to":[24,33,35,65,100,155,161,173],"distinguish":[25],"useful":[26,143],"information":[27],"from":[28],"task-irrelevant":[29],"perceptions,":[30],"enabling":[31],"them":[32],"generalize":[34],"unseen":[36],"environments":[37],"with":[38,53,142],"new":[39],"distractions.":[40],"Existing":[41],"works":[42],"approach":[43],"this":[44],"problem":[45],"using":[46],"data":[47],"augmentation":[48],"or":[49,171],"large":[50],"auxiliary":[51],"networks":[52],"additional":[54],"loss":[55],"functions.":[56],"We":[57,117],"introduce":[58],"MaDi,":[59,74],"a":[60,87,98,131],"novel":[61],"algorithm":[62,137],"that":[63,109],"learns":[64],"mask":[66,99],"distractions":[67],"reward":[70],"signal":[71],"only.":[72],"In":[73],"conventional":[76],"actor-critic":[77],"structure":[78],"deep":[80],"reinforcement":[81],"learning":[82,114],"is":[84],"complemented":[85],"small":[88],"third":[89],"sibling,":[90],"Masker.":[92],"This":[93],"lightweight":[94],"neural":[95],"network":[96,149],"generates":[97],"determine":[101],"what":[102],"actor":[104],"and":[105,130],"critic":[106],"receive,":[107],"such":[108],"they":[110],"can":[111],"focus":[112,141],"on":[113,120],"task.":[116],"run":[118],"experiments":[119],"DeepMind":[122],"Control":[123,128],"Generalization":[124],"Benchmark,":[125],"Distracting":[127],"Suite,":[129],"real":[132],"UR5":[133],"Robotic":[134],"Arm.":[135],"Our":[136],"improves":[138],"agent's":[140],"masks,":[144],"while":[145],"its":[146],"efficient":[147],"Masker":[148],"only":[150],"adds":[151],"0.2%":[152],"more":[153],"parameters":[154],"original":[157],"structure,":[158],"in":[159],"contrast":[160],"previous":[162],"work.":[163],"MaDi":[164],"consistently":[165],"achieves":[166],"generalization":[167],"results":[168],"better":[169],"than":[170],"competitive":[172],"state-of-the-art":[174],"methods.":[175]},"counts_by_year":[],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}