{"id":"https://openalex.org/W4403487385","doi":"https://doi.org/10.3233/faia240847","title":"Neural Reward Machines","display_name":"Neural Reward Machines","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487385","doi":"https://doi.org/10.3233/faia240847"},"language":"en","primary_location":{"id":"doi:10.3233/faia240847","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240847","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240847","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072591423","display_name":"Elena Umili","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Elena Umili","raw_affiliation_strings":["Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069605954","display_name":"Francesco Argenziano","orcid":"https://orcid.org/0009-0004-2028-7253"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Argenziano","raw_affiliation_strings":["Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016238183","display_name":"Roberto Capobianco","orcid":"https://orcid.org/0000-0002-2219-215X"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]},{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Roberto Capobianco","raw_affiliation_strings":["Sapienza University of Rome","Sony AI"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072591423"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.7962,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75013582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.24899999797344208,"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/T10320","display_name":"Neural Networks and Applications","score":0.24899999797344208,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.22030000388622284,"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/psychology","display_name":"Psychology","score":0.4190455973148346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38272640109062195}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4190455973148346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38272640109062195}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia240847","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240847","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:iris.uniroma1.it:11573/1725807","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1725807","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":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":{"id":"doi:10.3233/faia240847","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240847","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Non-markovian":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"tasks":[4],"are":[5],"very":[6],"hard":[7],"to":[8,20,37],"solve,":[9],"because":[10],"agents":[11],"must":[12],"consider":[13],"the":[14,24,39,60,104,135,150,159],"entire":[15],"history":[16],"of":[17,107,134,161,171],"state-action":[18],"pairs":[19],"act":[21],"rationally":[22],"in":[23,46,95,128,152],"environment.":[25],"Most":[26],"works":[27],"use":[28],"symbolic":[29,65,126],"formalisms":[30],"(as":[31],"Linear":[32],"Temporal":[33],"Logic":[34],"or":[35,52],"automata)":[36],"specify":[38],"temporally-extended":[40],"task.":[41],"These":[42],"approaches":[43],"only":[44],"work":[45],"finite":[47],"and":[48,63,93,118],"discrete":[49],"state":[50,62],"environments":[51,130],"continuous":[53],"problems":[54],"for":[55,90,157],"which":[56,100,142,164],"a":[57,64,70,172],"mapping":[58],"between":[59],"raw":[61],"interpretation":[66],"is":[67,101,165],"known":[68],"as":[69],"symbol":[71,115],"grounding":[72,116],"(SG)":[73],"function.":[74],"Here,":[75],"we":[76,119,148],"define":[77],"Neural":[78],"Reward":[79],"Machines":[80],"(NRM),":[81],"an":[82,155],"automata-based":[83],"neurosymbolic":[84],"framework":[85],"that":[86,121],"can":[87,123],"be":[88],"used":[89],"both":[91],"reasoning":[92],"learning":[94],"non-symbolic":[96,129],"non-markovian":[97],"RL":[98,112,140],"domains,":[99],"based":[102],"on":[103],"probabilistic":[105],"relaxation":[106],"Moore":[108],"Machines.":[109],"We":[110],"combine":[111],"with":[113],"semisupervised":[114],"(SSSG)":[117],"show":[120],"NRMs":[122],"exploit":[124],"high-level":[125],"knowledge":[127,133],"without":[131],"any":[132],"SG":[136],"function,":[137],"outperforming":[138],"Deep":[139],"methods":[141],"cannot":[143],"incorporate":[144],"prior":[145],"knowledge.":[146],"Moreover,":[147],"advance":[149],"research":[151],"SSSG,":[153],"proposing":[154],"algorithm":[156],"analysing":[158],"groundability":[160],"temporal":[162],"specifications,":[163],"more":[166],"efficient":[167],"than":[168],"baseline":[169],"techniques":[170],"factor":[173],"103.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}