{"id":"https://openalex.org/W3203259721","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534358","title":"Learning a Belief Representation for Delayed Reinforcement Learning","display_name":"Learning a Belief Representation for Delayed Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3203259721","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534358","mag":"3203259721"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5021875981","display_name":"Pierre Liotet","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Pierre Liotet","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046113487","display_name":"Erick Venneri","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Erick Venneri","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Restelli","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021875981"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69118989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.987500011920929,"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":0.9675999879837036,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8052507638931274},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7772932052612305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969647407531738},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.621829092502594},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5912929773330688},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5655857920646667},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5615966320037842},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5580341815948486},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5521480441093445},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5107953548431396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4728812575340271},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43230748176574707},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4274858832359314},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.415813148021698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3592236638069153},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2127048373222351},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1772189438343048}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8052507638931274},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7772932052612305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969647407531738},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.621829092502594},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5912929773330688},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5655857920646667},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5615966320037842},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5580341815948486},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5521480441093445},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5107953548431396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4728812575340271},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43230748176574707},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4274858832359314},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.415813148021698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3592236638069153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2127048373222351},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1772189438343048},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1208256","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/1208256","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8399999737739563,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W41554520","https://openalex.org/W1499408472","https://openalex.org/W1532688806","https://openalex.org/W1541084404","https://openalex.org/W1545148916","https://openalex.org/W1771410628","https://openalex.org/W1866230956","https://openalex.org/W1986278286","https://openalex.org/W2026076901","https://openalex.org/W2033523384","https://openalex.org/W2055921164","https://openalex.org/W2097797606","https://openalex.org/W2117864026","https://openalex.org/W2119567691","https://openalex.org/W2121092017","https://openalex.org/W2121863487","https://openalex.org/W2144913588","https://openalex.org/W2157331557","https://openalex.org/W2158782408","https://openalex.org/W2159566498","https://openalex.org/W2257979135","https://openalex.org/W2291973609","https://openalex.org/W2733312032","https://openalex.org/W2793100723","https://openalex.org/W2897445793","https://openalex.org/W2900559324","https://openalex.org/W2942608247","https://openalex.org/W2952032963","https://openalex.org/W2952838738","https://openalex.org/W2962938178","https://openalex.org/W2962990490","https://openalex.org/W2963047245","https://openalex.org/W2963090522","https://openalex.org/W2963403868","https://openalex.org/W2963524109","https://openalex.org/W2964227158","https://openalex.org/W2964252020","https://openalex.org/W2964907112","https://openalex.org/W2996037775","https://openalex.org/W3011120880","https://openalex.org/W3013672175","https://openalex.org/W3025864009","https://openalex.org/W3037207827","https://openalex.org/W3106462682","https://openalex.org/W3154264273","https://openalex.org/W4288363736","https://openalex.org/W4293849739","https://openalex.org/W4298023569","https://openalex.org/W4300802867","https://openalex.org/W4385245566","https://openalex.org/W6600231840","https://openalex.org/W6610566761","https://openalex.org/W6631864160","https://openalex.org/W6638018090","https://openalex.org/W6639317949","https://openalex.org/W6677939520","https://openalex.org/W6706363465","https://openalex.org/W6738536549","https://openalex.org/W6739901393","https://openalex.org/W6743300111","https://openalex.org/W6749111216","https://openalex.org/W6764926043"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2315999538"],"abstract_inverted_index":{"This":[0,109],"paper":[1],"considers":[2],"sequential":[3],"decision-making":[4],"problems":[5,141],"where":[6],"the":[7,24,28,33,38,47,55,58,73,76,92,97,103,106,129,132],"interactions":[8],"between":[9],"an":[10,69],"agent":[11],"and":[12,51,96,118,138],"its":[13,82],"environment":[14],"are":[15],"affected":[16,142],"by":[17,143],"delays.":[18,53,125,145],"Delays":[19],"may":[20],"be":[21,121],"present":[22],"in":[23,27,32,46,135],"state":[25,79,95],"observation,":[26],"action":[29],"execution,":[30],"or":[31],"reward":[34],"collection.":[35],"We":[36,84,126],"consider":[37],"delayed":[39,59],"Markov":[40],"Decision":[41],"Process":[42],"(MDP)":[43],"framework":[44],"both":[45,136],"case":[48],"of":[49,57,100,131],"deterministic":[50,116,137,144],"stochastic":[52,124,139],"Given":[54],"hardness":[56],"MDP":[60],"problem,":[61],"we":[62],"use":[63],"a":[64,86],"heuristic":[65],"approach":[66,134],"to":[67,80,113,123],"design":[68,85],"algorithm":[70,110],"that":[71],"uses":[72],"belief":[74],"over":[75,105],"current":[77],"unobserved":[78],"select":[81],"action.":[83],"self-attention":[87],"prediction":[88],"module":[89],"which,":[90],"given":[91],"last":[93],"observed":[94],"following":[98,107],"sequence":[99],"actions,":[101],"estimates":[102],"beliefs":[104],"states.":[108],"is":[111],"able":[112],"deal":[114],"with":[115],"delays":[117],"could":[119],"potentially":[120],"extended":[122],"empirically":[127],"evaluate":[128],"effectiveness":[130],"proposed":[133],"control":[140]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}