{"id":"https://openalex.org/W4294557525","doi":"https://doi.org/10.1007/s00521-022-07691-7","title":"Influence-aware memory architectures for deep reinforcement learning in POMDPs","display_name":"Influence-aware memory architectures for deep reinforcement learning in POMDPs","publication_year":2022,"publication_date":"2022-09-04","ids":{"openalex":"https://openalex.org/W4294557525","doi":"https://doi.org/10.1007/s00521-022-07691-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/40584429"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-022-07691-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07691-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07691-7.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07691-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046313876","display_name":"Miguel Suau","orcid":"https://orcid.org/0000-0003-2607-8992"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Miguel Suau","raw_affiliation_strings":["Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-2607-8992","affiliations":[{"raw_affiliation_string":"Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086693782","display_name":"Jinke He","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jinke He","raw_affiliation_strings":["Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036966730","display_name":"Elena Congeduti","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Elena Congeduti","raw_affiliation_strings":["Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068066221","display_name":"Rolf A. N. Starre","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rolf A. N. Starre","raw_affiliation_strings":["Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086126399","display_name":"Aleksander Czechowski","orcid":"https://orcid.org/0000-0002-6054-9842"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aleksander Czechowski","raw_affiliation_strings":["Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009493909","display_name":"Frans A. Oliehoek","orcid":"https://orcid.org/0000-0003-4372-5055"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frans A. Oliehoek","raw_affiliation_strings":["Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046313876"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2775,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63011434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"37","issue":"19","first_page":"13145","last_page":"13161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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/T10260","display_name":"Software Engineering Research","score":0.9818999767303467,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.8636918067932129},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8064025044441223},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7139443159103394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6179423332214355},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5683266520500183},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5528476238250732},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5199976563453674},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49156054854393005},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.47546595335006714},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4546040892601013},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4457818865776062},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.418472021818161},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1504582166671753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636918067932129},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8064025044441223},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7139443159103394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6179423332214355},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5683266520500183},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5528476238250732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5199976563453674},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49156054854393005},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.47546595335006714},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4546040892601013},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4457818865776062},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.418472021818161},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1504582166671753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s00521-022-07691-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07691-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07691-7.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmid:40584429","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40584429","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computing & applications","raw_type":null},{"id":"pmh:oai:europepmc.org:11012209","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12204899","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:tudelft.nl:uuid:7cf40b53-7353-4e8d-ac41-c6bbe052ecbe","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:7cf40b53-7353-4e8d-ac41-c6bbe052ecbe","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1007/s00521-022-07691-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07691-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07691-7.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1073366937","display_name":"Influence-based Decision-making in Uncertain Environments","funder_award_id":"758824","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4836127256","display_name":"Influence-based Decision-making in Uncertain Environments","funder_award_id":"758824","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4294557525.pdf","grobid_xml":"https://content.openalex.org/works/W4294557525.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1541084404","https://openalex.org/W1570690983","https://openalex.org/W1576718874","https://openalex.org/W1687873425","https://openalex.org/W1749432972","https://openalex.org/W1902237438","https://openalex.org/W2061504687","https://openalex.org/W2064675550","https://openalex.org/W2109910161","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2157331557","https://openalex.org/W2334782222","https://openalex.org/W2499811908","https://openalex.org/W2522489477","https://openalex.org/W2810602713","https://openalex.org/W2903709398","https://openalex.org/W2914584698","https://openalex.org/W2963053311","https://openalex.org/W2963725394","https://openalex.org/W2964184826","https://openalex.org/W2999905431","https://openalex.org/W3012502279","https://openalex.org/W3020913839","https://openalex.org/W3099518626","https://openalex.org/W3101438731","https://openalex.org/W4212863985","https://openalex.org/W4214717370","https://openalex.org/W4249992252","https://openalex.org/W6602539713","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2104042711","https://openalex.org/W4206221578"],"abstract_inverted_index":{"Abstract":[0],"Due":[1],"to":[2,16,25,32,47,56,95,107,136,204],"its":[3],"perceptual":[4],"limitations,":[5],"an":[6],"agent":[7],"may":[8],"have":[9,59],"too":[10],"little":[11],"information":[12,115,135,170],"about":[13],"the":[14,29,84,89,92,100,126,129,143,152,161,166,169],"environment":[15],"act":[17],"optimally.":[18],"In":[19,69],"such":[20],"cases,":[21],"it":[22],"is":[23,121],"important":[24],"keep":[26],"track":[27],"of":[28,91,114,160,168],"action-observation":[30],"history":[31],"uncover":[33],"hidden":[34,101],"state":[35,102],"information.":[36,103],"Recent":[37],"deep":[38],"reinforcement":[39],"learning":[40],"methods":[41,199],"use":[42],"recurrent":[43,93,153,180],"neural":[44,174],"networks":[45],"(RNN)":[46],"memorize":[48],"past":[49],"observations.":[50],"However,":[51],"these":[52],"models":[53],"are":[54],"expensive":[55],"train":[57],"and":[58,186,194],"convergence":[60],"difficulties,":[61],"especially":[62],"when":[63],"dealing":[64],"with":[65,171],"high":[66],"dimensional":[67],"data.":[68],"this":[70],"paper,":[71],"we":[72,176],"propose":[73],"influence-aware":[74],"memory":[75,80],",":[76],"a":[77,157,172],"theoretically":[78],"inspired":[79],"architecture":[81],"that":[82,98,200],"alleviates":[83],"training":[85,184],"difficulties":[86],"by":[87,150],"restricting":[88],"input":[90],"layers":[94,154],"those":[96],"variables":[97,163],"influence":[99],"Moreover,":[104],"as":[105],"opposed":[106],"standard":[108,179],"RNNs,":[109],"in":[110,142,183],"which":[111],"every":[112],"piece":[113],"used":[116],"for":[117,128],"estimating":[118],"Q":[119],"values":[120],"inevitably":[122],"fed":[123],"back":[124],"into":[125],"network":[127],"next":[130],"prediction,":[131],"our":[132],"model":[133],"allows":[134],"flow":[137],"without":[138],"being":[139],"necessarily":[140],"stored":[141],"RNN\u2019s":[144],"internal":[145],"memory.":[146],"Results":[147],"indicate":[148],"that,":[149],"letting":[151],"focus":[155],"on":[156],"small":[158],"fraction":[159],"observation":[162],"while":[164],"processing":[165],"rest":[167],"feedforward":[173],"network,":[175],"can":[177],"outperform":[178],"architectures":[181],"both":[182],"speed":[185],"policy":[187],"performance.":[188],"This":[189],"approach":[190],"also":[191],"reduces":[192],"runtime":[193],"obtains":[195],"better":[196],"scores":[197],"than":[198],"stack":[201],"multiple":[202],"observations":[203],"remove":[205],"partial":[206],"observability.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}