{"id":"https://openalex.org/W4226109878","doi":"https://doi.org/10.1109/bigdata52589.2021.9671827","title":"InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem","display_name":"InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4226109878","doi":"https://doi.org/10.1109/bigdata52589.2021.9671827"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671827","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","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/A5039146131","display_name":"Markel Sanz Ausin","orcid":"https://orcid.org/0000-0002-4526-9252"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Markel Sanz Ausin","raw_affiliation_strings":["North Carolina State University, Raleigh, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027571540","display_name":"Hamoon Azizsoltani","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamoon Azizsoltani","raw_affiliation_strings":["North Carolina State University, Raleigh, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025015480","display_name":"Song Hyun Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Ju","raw_affiliation_strings":["North Carolina State University, Raleigh, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103202565","display_name":"Yeo Jin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yeo Jin Kim","raw_affiliation_strings":["North Carolina State University, Raleigh, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090231772","display_name":"Min Chi","orcid":"https://orcid.org/0000-0003-1765-7837"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Chi","raw_affiliation_strings":["North Carolina State University, Raleigh, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039146131"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.6283,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72359319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1337","last_page":"1348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9397000074386597,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9218999743461609,"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":0.9106875658035278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010258674621582},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7503625750541687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6256364583969116},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5772203207015991},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47692081332206726},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46830427646636963},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4447265565395355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.413513720035553}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9106875658035278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010258674621582},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7503625750541687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6256364583969116},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5772203207015991},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47692081332206726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46830427646636963},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4447265565395355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.413513720035553},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671827","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1569296262","https://openalex.org/W1591675293","https://openalex.org/W1993397663","https://openalex.org/W1999874108","https://openalex.org/W2045031658","https://openalex.org/W2098774185","https://openalex.org/W2098877483","https://openalex.org/W2103626435","https://openalex.org/W2117675763","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2491675558","https://openalex.org/W2610925718","https://openalex.org/W2665657980","https://openalex.org/W2766447205","https://openalex.org/W2789634097","https://openalex.org/W2809013025","https://openalex.org/W2891772748","https://openalex.org/W2896893468","https://openalex.org/W2902907165","https://openalex.org/W2912071375","https://openalex.org/W2947373402","https://openalex.org/W2951799221","https://openalex.org/W2963523627","https://openalex.org/W2964096423","https://openalex.org/W2966387108","https://openalex.org/W2990032740","https://openalex.org/W2996037775","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3092872653","https://openalex.org/W3108636033","https://openalex.org/W3133533407","https://openalex.org/W3154264273","https://openalex.org/W3168837055","https://openalex.org/W3173852058","https://openalex.org/W3206540493","https://openalex.org/W4287274316","https://openalex.org/W4287998216","https://openalex.org/W4288029271","https://openalex.org/W4301178047","https://openalex.org/W6635261211","https://openalex.org/W6674657456","https://openalex.org/W6674884181","https://openalex.org/W6677555207","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6722970529","https://openalex.org/W6746030470","https://openalex.org/W6748875114","https://openalex.org/W6749859622","https://openalex.org/W6762737111","https://openalex.org/W6766967640","https://openalex.org/W6767226293","https://openalex.org/W6772005887","https://openalex.org/W6777387433","https://openalex.org/W6784654296","https://openalex.org/W6784718507","https://openalex.org/W6785140329","https://openalex.org/W6791099515"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Rewards":[0],"are":[1,25,67,204,209],"the":[2,12,31,79,93,97,155,191],"critical":[3],"signals":[4],"for":[5,189],"Reinforcement":[6],"Learning":[7],"(RL)":[8],"algorithms":[9],"to":[10,81,91,140,163,177],"learn":[11],"desired":[13],"behavior":[14],"in":[15,29,49,147,194],"a":[16,44,82,113,115,128,164,195],"sequential":[17],"multi-step":[18],"learning":[19,32],"task.":[20,132],"However,":[21],"when":[22,65,201],"these":[23],"rewards":[24,61,66,95,137,146,203],"delayed":[26,68,98,145,178],"and":[27,46,99,117,121,127,144,151,183],"noisy":[28,100,180],"nature,":[30],"process":[33],"becomes":[34],"more":[35],"challenging.":[36],"The":[37,102,133],"temporal":[38,192],"Credit":[39],"Assignment":[40],"Problem":[41],"(CAP)":[42],"is":[43,138,160,175],"well-known":[45],"challenging":[47],"task":[48],"AI.":[50],"While":[51],"RL,":[52,55],"especially":[53],"Deep":[54],"often":[56],"works":[57],"well":[58],"with":[59,150],"immediate":[60,94,143,202],"but":[62],"may":[63],"fail":[64],"or":[69,71,179,207],"noisy,":[70],"both.":[72],"In":[73],"this":[74],"work,":[75],"we":[76],"propose":[77],"delegating":[78],"CAP":[80,193],"Neural":[83],"Network-based":[84],"algorithm":[85],"named":[86],"InferNet":[87,105,136,174],"that":[88,141,173],"explicitly":[89],"learns":[90],"infer":[92],"from":[96],"rewards.":[101],"effectiveness":[103,134],"of":[104,135,142,198],"was":[106],"evaluated":[107],"on":[108],"three":[109],"online":[110],"RL":[111,124,157,199],"tasks:":[112,125],"GridWorld,":[114],"CartPole,":[116],"40":[118],"Atari":[119],"games;":[120],"two":[122,148],"offline":[123,156],"GridWorld":[126],"real-life":[129],"Sepsis":[130],"treatment":[131],"compared":[139,162],"settings:":[149],"without":[152],"noise.":[153],"For":[154],"tasks,":[158,200],"it":[159,184],"also":[161],"strong":[165],"baseline,":[166],"InferGP":[167],"[7].":[168],"Overall,":[169],"our":[170],"results":[171],"show":[172],"robust":[176],"reward":[181],"functions,":[182],"could":[185],"be":[186],"used":[187],"effectively":[188],"solving":[190],"wide":[196],"range":[197],"not":[205],"available":[206],"they":[208],"noisy.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}