{"id":"https://openalex.org/W4404307235","doi":"https://doi.org/10.1109/access.2024.3497589","title":"Knowledge Transfer in Deep Reinforcement Learning via an RL-Specific GAN-Based Correspondence Function","display_name":"Knowledge Transfer in Deep Reinforcement Learning via an RL-Specific GAN-Based Correspondence Function","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404307235","doi":"https://doi.org/10.1109/access.2024.3497589"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3497589","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3497589","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3497589","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008762593","display_name":"Marko Ruman","orcid":"https://orcid.org/0000-0001-9349-377X"},"institutions":[{"id":"https://openalex.org/I4210119419","display_name":"Czech Academy of Sciences, Institute of Information Theory and Automation","ror":"https://ror.org/03h1hsz49","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210119419"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Marko Ruman","raw_affiliation_strings":["Department of Adaptive Systems, Institute of Information Theory and Automation, Czech Academy of Sciences, Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Adaptive Systems, Institute of Information Theory and Automation, Czech Academy of Sciences, Prague, Czech Republic","institution_ids":["https://openalex.org/I4210119419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016153096","display_name":"Tatiana V. Guy","orcid":"https://orcid.org/0000-0003-1017-0727"},"institutions":[{"id":"https://openalex.org/I4210119419","display_name":"Czech Academy of Sciences, Institute of Information Theory and Automation","ror":"https://ror.org/03h1hsz49","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210119419"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tatiana V. Guy","raw_affiliation_strings":["Department of Adaptive Systems, Institute of Information Theory and Automation, Czech Academy of Sciences, Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Adaptive Systems, Institute of Information Theory and Automation, Czech Academy of Sciences, Prague, Czech Republic","institution_ids":["https://openalex.org/I4210119419"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008762593"],"corresponding_institution_ids":["https://openalex.org/I4210119419"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18707911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"177204","last_page":"177218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.8618999719619751,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.8618999719619751,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7646999955177307,"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":0.7757678031921387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.71296226978302},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5526408553123474},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5076783895492554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47818735241889954},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.447061151266098},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08400455117225647},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07858556509017944}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7757678031921387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71296226978302},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5526408553123474},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5076783895492554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47818735241889954},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.447061151266098},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08400455117225647},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07858556509017944},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3497589","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3497589","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5fe6f68baf904dba9842fefd8edf0efd","is_oa":true,"landing_page_url":"https://doaj.org/article/5fe6f68baf904dba9842fefd8edf0efd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 177204-177218 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3497589","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3497589","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5368210490","display_name":null,"funder_award_id":"COST Action CA21169","funder_id":"https://openalex.org/F4320320366","funder_display_name":"European Cooperation in Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320366","display_name":"European Cooperation in Science and Technology","ror":"https://ror.org/01bstzn19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2060993602","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2165698076","https://openalex.org/W2765424254","https://openalex.org/W2902907165","https://openalex.org/W2950689937","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963390419","https://openalex.org/W2963917969","https://openalex.org/W3007869767","https://openalex.org/W3021988786","https://openalex.org/W3035756007","https://openalex.org/W3136181012","https://openalex.org/W3164005523","https://openalex.org/W3203069471","https://openalex.org/W3206394619","https://openalex.org/W4249736682","https://openalex.org/W4321780050","https://openalex.org/W4323020953","https://openalex.org/W4383112908","https://openalex.org/W4385245566","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6689515257","https://openalex.org/W6703110798","https://openalex.org/W6718190810","https://openalex.org/W6727249380","https://openalex.org/W6734074887","https://openalex.org/W6736469832","https://openalex.org/W6752601656","https://openalex.org/W6754615820","https://openalex.org/W6756256016","https://openalex.org/W6762581443","https://openalex.org/W6785684253","https://openalex.org/W6786816963"],"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/W2586732548","https://openalex.org/W3123837699"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,37,154],"learning":[2],"has":[3],"demonstrated":[4],"superhuman":[5],"performance":[6,131],"in":[7,92,104,136,152],"complex":[8],"decision-making":[9],"tasks,":[10,67],"but":[11],"it":[12],"struggles":[13],"with":[14,53],"generalization":[15,151],"and":[16,65,68,95],"knowledge":[17,42,90,98,150],"reuse\u2014key":[18],"aspects":[19],"of":[20,139],"true":[21],"intelligence.":[22],"This":[23],"article":[24],"introduces":[25],"a":[26,101,108],"novel":[27],"approach":[28],"that":[29,144],"modifies":[30],"Cycle":[31,124],"Generative":[32,120,125],"Adversarial":[33,121,126],"Networks":[34,122,127],"specifically":[35],"for":[36,107],"learning,":[38],"enabling":[39],"effective":[40],"one-to-one":[41],"transfer":[43,91,99],"between":[44,63],"two":[45,54],"tasks.":[46],"Our":[47],"method":[48,87,147],"enhances":[49],"the":[50,75,81,113,137,145],"loss":[51],"function":[52],"new":[55],"components:":[56],"model":[57],"loss,":[58],"which":[59,70],"captures":[60],"dynamic":[61],"relationships":[62],"source":[64],"target":[66,76],"Q-loss,":[69],"identifies":[71],"states":[72],"significantly":[73],"influencing":[74],"decision":[77],"policy.":[78],"Tested":[79],"on":[80,112],"2-D":[82],"Atari":[83],"game":[84],"Pong,":[85],"our":[86],"achieved":[88],"100%":[89,97],"identical":[93],"tasks":[94],"either":[96],"or":[100,123],"30%":[102],"reduction":[103],"training":[105,133],"time":[106],"rotated":[109],"task,":[110],"depending":[111],"network":[114],"architecture.":[115],"In":[116],"contrast,":[117],"using":[118],"standard":[119],"led":[128],"to":[129],"worse":[130],"than":[132],"from":[134],"scratch":[135],"majority":[138],"cases.":[140],"The":[141],"results":[142],"demonstrate":[143],"proposed":[146],"ensured":[148],"enhanced":[149],"deep":[153],"learning.":[155]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}