{"id":"https://openalex.org/W4312788949","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892560","title":"Concurrent Credit Assignment for Data-efficient Reinforcement Learning","display_name":"Concurrent Credit Assignment for Data-efficient Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312788949","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892560"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892560","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 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/A5002950216","display_name":"Emmanuel Dauc\u00e9","orcid":"https://orcid.org/0000-0001-6596-8168"},"institutions":[{"id":"https://openalex.org/I4210142724","display_name":"Centrale Marseille","ror":"https://ror.org/040baw385","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142724"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210138220","display_name":"Institut de Neurosciences de la Timone","ror":"https://ror.org/043hw6336","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210096427","https://openalex.org/I4210138220"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Emmanuel Dauce","raw_affiliation_strings":["Institut de Neurosciences de la Timone Centrale Marseille, CNRS,Marseille,France","Institut de Neurosciences de la Timone Centrale Marseille, CNRS, Marseille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de Neurosciences de la Timone Centrale Marseille, CNRS,Marseille,France","institution_ids":["https://openalex.org/I4210138220","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Institut de Neurosciences de la Timone Centrale Marseille, CNRS, Marseille, France","institution_ids":["https://openalex.org/I4210138220","https://openalex.org/I4210142724","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002950216"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210138220","https://openalex.org/I4210142724"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1664458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","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":0.98580002784729,"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":0.98580002784729,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9289000034332275,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7994588017463684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7196776866912842},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41026774048805237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3989798426628113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3409980535507202},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08761802315711975}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7994588017463684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196776866912842},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41026774048805237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3989798426628113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3409980535507202},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08761802315711975},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892560","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1713439590","display_name":"COmpREssing networks and GRAPHs for efficIEnt computing","funder_award_id":"ANR-20-CE23-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1515851193","https://openalex.org/W1941248864","https://openalex.org/W1959608418","https://openalex.org/W2056354534","https://openalex.org/W2101234009","https://openalex.org/W2101524054","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2128174349","https://openalex.org/W2135886642","https://openalex.org/W2152726590","https://openalex.org/W2417786368","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2787938642","https://openalex.org/W2799151646","https://openalex.org/W2898757087","https://openalex.org/W2902298341","https://openalex.org/W2949475445","https://openalex.org/W2962730405","https://openalex.org/W2963276097","https://openalex.org/W2963277051","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2978644431","https://openalex.org/W2996251520","https://openalex.org/W2999091228","https://openalex.org/W3022265613","https://openalex.org/W3041202696","https://openalex.org/W3190513196","https://openalex.org/W4237591687","https://openalex.org/W4287907550","https://openalex.org/W4298857966","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6640661648","https://openalex.org/W6640963894","https://openalex.org/W6675354045","https://openalex.org/W6679266861","https://openalex.org/W6682656681","https://openalex.org/W6685757253","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6730641667","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747924173","https://openalex.org/W6748603076","https://openalex.org/W6748839928","https://openalex.org/W6750186571","https://openalex.org/W6757058172","https://openalex.org/W6769196924","https://openalex.org/W6780070897","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"The":[0,20],"capacity":[1],"to":[2,73,141],"widely":[3],"sample":[4],"the":[5,33,37,41,65,68,82,85,89,92,96,103,106,112,122,125,146,162,165],"state":[6],"and":[7,88,105,115,157,164],"action":[8,135],"spaces":[9],"is":[10,32,48,139,150],"a":[11,44,55,71,75,153],"key":[12],"ingredient":[13],"toward":[14],"building":[15],"effective":[16],"reinforcement":[17],"learning":[18],"algorithms.":[19],"method":[21],"presented":[22],"in":[23,145,152,160],"this":[24,137],"paper":[25],"relies":[26],"on":[27,64,128,132],"an":[28,60,129],"occupancy":[29,57,86,107],"model,":[30],"that":[31,47,116,149],"empirical":[34],"distribution":[35],"of":[36,51,67,84,91,95,124],"states":[38,118],"encountered":[39],"by":[40],"agent":[42],"under":[43,54],"given":[45],"policy,":[46],"its":[49],"\u201cdomain":[50],"operation\u201d.":[52],"Then,":[53],"uniform":[56],"prior":[58],"assumption,":[59],"evidence":[61],"lower":[62],"bound":[63],"parameters":[66],"policy":[69,104],"provides":[70],"way":[72],"express":[74],"balance":[76],"between":[77],"two":[78],"concurrent":[79],"tendencies,":[80],"namely":[81],"widening":[83],"space":[87],"maximization":[90],"rewards,":[93],"reminding":[94],"classical":[97],"exploration/exploitation":[98],"trade-off.":[99],"During":[100],"training,":[101],"both":[102,161],"model":[108],"are":[109,119],"updated":[110],"as":[111],"exploration":[113],"progresses,":[114],"new":[117],"undisclosed":[120],"during":[121],"course":[123],"training.":[126],"Implemented":[127],"actor-critic":[130],"off-policy":[131],"classic":[133],"continuous":[134],"benchmarks,":[136],"approach":[138],"shown":[140],"provide":[142],"significant":[143],"increase":[144],"sampling":[147],"efficacy,":[148],"reflected":[151],"reduced":[154],"training":[155],"time":[156],"higher":[158],"returns,":[159],"dense":[163],"sparse":[166],"rewards":[167],"cases.":[168]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}