{"id":"https://openalex.org/W2976021111","doi":"https://doi.org/10.24963/ijcai.2020/376","title":"Only Relevant Information Matters: Filtering Out Noisy Samples To Boost RL","display_name":"Only Relevant Information Matters: Filtering Out Noisy Samples To Boost RL","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W2976021111","doi":"https://doi.org/10.24963/ijcai.2020/376","mag":"2976021111"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/376","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/376","pdf_url":"https://www.ijcai.org/proceedings/2020/0376.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0376.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045192384","display_name":"Yannis Flet-Berliac","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210104444","display_name":"Afterschool Alliance","ror":"https://ror.org/01bd8yz25","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104444"]},{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Yannis Flet-Berliac","raw_affiliation_strings":["CNRS","CRIStAL Univ. Lille","SequeL Inria","Sequential Learning","Scool","Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS","institution_ids":[]},{"raw_affiliation_string":"CRIStAL Univ. Lille","institution_ids":[]},{"raw_affiliation_string":"SequeL Inria","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Sequential Learning","institution_ids":[]},{"raw_affiliation_string":"Scool","institution_ids":["https://openalex.org/I4210104444"]},{"raw_affiliation_string":"Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189","institution_ids":["https://openalex.org/I4210115519","https://openalex.org/I4387153239"]}]},{"author_position":"last","author":{"id":null,"display_name":"Philippe Preux","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210104444","display_name":"Afterschool Alliance","ror":"https://ror.org/01bd8yz25","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104444"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Philippe Preux","raw_affiliation_strings":["CNRS","CRIStAL Univ. Lille","SequeL Inria","Sequential Learning","Scool"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS","institution_ids":[]},{"raw_affiliation_string":"CRIStAL Univ. Lille","institution_ids":[]},{"raw_affiliation_string":"SequeL Inria","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Sequential Learning","institution_ids":[]},{"raw_affiliation_string":"Scool","institution_ids":["https://openalex.org/I4210104444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4062,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67962991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2711","last_page":"2717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.7804282307624817},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.713363528251648},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.672876238822937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6698045134544373},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.607930064201355},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5798916220664978},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.5197217464447021},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.498258113861084},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4784829020500183},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4385475516319275},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.4273834228515625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41339343786239624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40171074867248535},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3283464312553406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2625693678855896},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2611524164676666}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7804282307624817},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.713363528251648},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.672876238822937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6698045134544373},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.607930064201355},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5798916220664978},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5197217464447021},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.498258113861084},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4784829020500183},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4385475516319275},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.4273834228515625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41339343786239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40171074867248535},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3283464312553406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2625693678855896},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2611524164676666},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.24963/ijcai.2020/376","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/376","pdf_url":"https://www.ijcai.org/proceedings/2020/0376.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.04025","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.04025","pdf_url":"https://arxiv.org/pdf/1904.04025","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:HAL:hal-02091547v5","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02091547","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IJCAI 2020 - International Joint Conference on Artificial Intelligence","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-02091547v6","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02091547","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IJCAI 2020 - International Joint Conference on Artificial Intelligence, Jul 2020, Yokohama, Japan. ⟨10.24963/ijcai.2020/376⟩","raw_type":"Conference papers"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/21760","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/21760","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/57542","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/57542","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/376","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/376","pdf_url":"https://www.ijcai.org/proceedings/2020/0376.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2976021111.pdf","grobid_xml":"https://content.openalex.org/works/W2976021111.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W58921469","https://openalex.org/W107583932","https://openalex.org/W1191599655","https://openalex.org/W1585861384","https://openalex.org/W1863227302","https://openalex.org/W1907796993","https://openalex.org/W1970789124","https://openalex.org/W1987150989","https://openalex.org/W2057327562","https://openalex.org/W2091565802","https://openalex.org/W2095705004","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2121103318","https://openalex.org/W2121863487","https://openalex.org/W2125612430","https://openalex.org/W2130801532","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2593044849","https://openalex.org/W2736601468","https://openalex.org/W2749928749","https://openalex.org/W2781726626","https://openalex.org/W2890208753","https://openalex.org/W2951507724","https://openalex.org/W2962902376","https://openalex.org/W2963095800","https://openalex.org/W2963184621","https://openalex.org/W2963313316","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964006217","https://openalex.org/W2964043796","https://openalex.org/W2971239080","https://openalex.org/W2979820775","https://openalex.org/W2982388247","https://openalex.org/W2998268493","https://openalex.org/W3103780890","https://openalex.org/W4230563027","https://openalex.org/W4236679173","https://openalex.org/W4251193772","https://openalex.org/W4285719527","https://openalex.org/W4297797010","https://openalex.org/W4298023569","https://openalex.org/W4302570325","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W4387995274","https://openalex.org/W4390482521"],"abstract_inverted_index":{"In":[0,89,120],"reinforcement":[1],"learning,":[2],"policy":[3,8,26,40,117],"gradient":[4,59,118],"algorithms":[5],"optimize":[6],"the":[7,58,69,75,81,86,114,126,157],"directly":[9],"and":[10,85,105,163,170],"rely":[11],"on":[12,24,136,161,167],"sampling":[13,20,36],"efficiently":[14],"an":[15],"environment.":[16],"Nevertheless,":[17],"while":[18],"most":[19,158],"procedures":[21],"are":[22,55,100],"based":[23],"direct":[25],"sampling,":[27],"self-performance":[28],"measures":[29],"could":[30],"be":[31],"used":[32],"to":[33,38,68,96,102,129],"improve":[34,113],"such":[35],"prior":[37],"each":[39],"update.":[41,60],"Following":[42],"this":[43,90,94,109,121],"line":[44],"of":[45,63,71,80,116,139],"thought,":[46],"we":[47,92,106],"introduce":[48,125],"SAUNA,":[49],"a":[50,78,137],"method":[51,128],"where":[52],"non-informative":[53],"transitions":[54],"rejected":[56],"from":[57],"The":[61],"level":[62],"information":[64],"is":[65],"estimated":[66],"according":[67],"fraction":[70],"variance":[72],"explained":[73],"by":[74],"value":[76],"function:":[77],"measure":[79],"discrepancy":[82],"between":[83],"V":[84],"empirical":[87],"returns.":[88],"work,":[91],"use":[93],"criterion":[95],"select":[97],"samples":[98,155],"that":[99,108],"useful":[101],"learn":[103],"from,":[104],"demonstrate":[107],"selection":[110],"can":[111],"significantly":[112,145],"performance":[115,169],"methods.":[119],"paper:":[122],"(a)":[123],"We":[124,133,149],"SAUNA":[127,144,152],"filter":[130],"transitions.":[131],"(b)":[132],"conduct":[134],"experiments":[135],"set":[138],"benchmark":[140],"continuous":[141],"control":[142],"problems.":[143],"improves":[146],"performance.":[147],"(c)":[148],"investigate":[150],"how":[151],"reliably":[153],"selects":[154],"with":[156],"positive":[159],"impact":[160],"learning":[162],"study":[164],"its":[165],"improvement":[166],"both":[168],"sample":[171],"efficiency.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}