{"id":"https://openalex.org/W4318602992","doi":"https://doi.org/10.1109/ssci51031.2022.10022229","title":"On Neural Consolidation for Transfer in Reinforcement Learning","display_name":"On Neural Consolidation for Transfer in Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-04","ids":{"openalex":"https://openalex.org/W4318602992","doi":"https://doi.org/10.1109/ssci51031.2022.10022229"},"language":"en","primary_location":{"id":"doi:10.1109/ssci51031.2022.10022229","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci51031.2022.10022229","pdf_url":null,"source":{"id":"https://openalex.org/S4363605327","display_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","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 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081844070","display_name":"Valentin Guillet","orcid":null},"institutions":[{"id":"https://openalex.org/I193033237","display_name":"Institut Sup\u00e9rieur de l'A\u00e9ronautique et de l'Espace (ISAE-SUPAERO)","ror":"https://ror.org/04gyj6s21","country_code":"FR","type":"education","lineage":["https://openalex.org/I193033237"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Valentin Guillet","raw_affiliation_strings":["Université de Toulouse,ISAE-Supaero,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Toulouse,ISAE-Supaero,France","institution_ids":["https://openalex.org/I193033237"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001743328","display_name":"Dennis G. Wilson","orcid":"https://orcid.org/0000-0003-2414-0051"},"institutions":[{"id":"https://openalex.org/I193033237","display_name":"Institut Sup\u00e9rieur de l'A\u00e9ronautique et de l'Espace (ISAE-SUPAERO)","ror":"https://ror.org/04gyj6s21","country_code":"FR","type":"education","lineage":["https://openalex.org/I193033237"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dennis Wilson","raw_affiliation_strings":["Université de Toulouse,ISAE-Supaero,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Toulouse,ISAE-Supaero,France","institution_ids":["https://openalex.org/I193033237"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008608798","display_name":"Carlos Aguilar-Melchor","orcid":"https://orcid.org/0000-0003-2745-884X"},"institutions":[{"id":"https://openalex.org/I4210129779","display_name":"Sandbox Learning (United States)","ror":"https://ror.org/03pdrba07","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Aguilar-Melchor","raw_affiliation_strings":["SandboxAQ,France","SandboxAQ, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SandboxAQ,France","institution_ids":["https://openalex.org/I4210129779"]},{"raw_affiliation_string":"SandboxAQ, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049708660","display_name":"Emmanuel Rachelson","orcid":"https://orcid.org/0000-0002-8559-1617"},"institutions":[{"id":"https://openalex.org/I193033237","display_name":"Institut Sup\u00e9rieur de l'A\u00e9ronautique et de l'Espace (ISAE-SUPAERO)","ror":"https://ror.org/04gyj6s21","country_code":"FR","type":"education","lineage":["https://openalex.org/I193033237"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Rachelson","raw_affiliation_strings":["Université de Toulouse,ISAE-Supaero,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Toulouse,ISAE-Supaero,France","institution_ids":["https://openalex.org/I193033237"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19684644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"867","last_page":"874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.993399977684021,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9822999835014343,"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/computer-science","display_name":"Computer science","score":0.7837651968002319},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7242810130119324},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6656451225280762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6643304228782654},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.527978241443634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5193566083908081},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5170236825942993},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.513295590877533},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.44231632351875305},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4277001619338989},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.07358092069625854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837651968002319},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7242810130119324},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6656451225280762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6643304228782654},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.527978241443634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5193566083908081},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5170236825942993},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.513295590877533},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.44231632351875305},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4277001619338989},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.07358092069625854},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci51031.2022.10022229","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci51031.2022.10022229","pdf_url":null,"source":{"id":"https://openalex.org/S4363605327","display_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","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 IEEE Symposium Series on Computational Intelligence (SSCI)","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":52,"referenced_works":["https://openalex.org/W54398672","https://openalex.org/W2047057213","https://openalex.org/W2097381042","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2201581102","https://openalex.org/W2294370754","https://openalex.org/W2473930607","https://openalex.org/W2474280151","https://openalex.org/W2560647685","https://openalex.org/W2583761661","https://openalex.org/W2604763608","https://openalex.org/W2735995851","https://openalex.org/W2761873684","https://openalex.org/W2788388592","https://openalex.org/W2804175194","https://openalex.org/W2920362155","https://openalex.org/W2963540014","https://openalex.org/W2963559848","https://openalex.org/W2964189064","https://openalex.org/W2981707302","https://openalex.org/W3008449794","https://openalex.org/W3106539628","https://openalex.org/W4214717370","https://openalex.org/W4230616333","https://openalex.org/W4295883599","https://openalex.org/W4298174377","https://openalex.org/W4301163820","https://openalex.org/W4301761856","https://openalex.org/W4319988532","https://openalex.org/W6602170065","https://openalex.org/W6638523607","https://openalex.org/W6674600207","https://openalex.org/W6685726866","https://openalex.org/W6687681856","https://openalex.org/W6720926796","https://openalex.org/W6732467815","https://openalex.org/W6732837357","https://openalex.org/W6736057607","https://openalex.org/W6738602802","https://openalex.org/W6740879895","https://openalex.org/W6741087337","https://openalex.org/W6741217325","https://openalex.org/W6742852309","https://openalex.org/W6747909518","https://openalex.org/W6750253780","https://openalex.org/W6751591294","https://openalex.org/W6760405395","https://openalex.org/W6764247177","https://openalex.org/W6771876938","https://openalex.org/W6774313160","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Although":[0],"transfer":[1,60,89],"learning":[2],"is":[3,33],"considered":[4],"to":[5,53,79,102,110],"be":[6,27],"a":[7,49,80],"milestone":[8],"in":[9,58,113],"deep":[10],"reinforcement":[11],"learning,":[12],"the":[13,43,56,98,103],"mechanisms":[14],"behind":[15],"it":[16],"are":[17],"still":[18,34],"poorly":[19],"understood.":[20],"In":[21,38],"particular,":[22],"predicting":[23],"if":[24],"knowledge":[25,71],"can":[26,61],"transferred":[28],"between":[29,105],"two":[30],"given":[31],"tasks":[32,78],"an":[35],"unresolved":[36],"problem.":[37],"this":[39],"work,":[40],"we":[41,64,84],"explore":[42],"use":[44],"of":[45,115],"network":[46],"distillation":[47,67],"as":[48],"feature":[50],"extraction":[51],"method":[52],"better":[54],"understand":[55],"context":[57],"which":[59],"occur.":[62],"Notably,":[63],"show":[65],"that":[66],"does":[68],"not":[69],"prevent":[70],"transfer,":[72],"including":[73],"when":[74],"transferring":[75],"from":[76],"multiple":[77],"new":[81],"one,":[82],"and":[83],"compare":[85],"these":[86],"results":[87],"with":[88],"without":[90],"prior":[91],"distillation.":[92],"We":[93],"focus":[94],"our":[95],"work":[96],"on":[97],"Atari":[99],"benchmark":[100],"due":[101],"variability":[104],"different":[106],"games,":[107],"but":[108],"also":[109],"their":[111],"similarities":[112],"terms":[114],"visual":[116],"features.":[117]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}