{"id":"https://openalex.org/W4285264760","doi":"https://doi.org/10.1109/access.2022.3178194","title":"A Swapping Target Q-Value Technique for Data Augmentation in Offline Reinforcement Learning","display_name":"A Swapping Target Q-Value Technique for Data Augmentation in Offline Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285264760","doi":"https://doi.org/10.1109/access.2022.3178194"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3178194","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3178194","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09782432.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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://ieeexplore.ieee.org/ielx7/6287639/6514899/09782432.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028014790","display_name":"Ho-Taek Joo","orcid":"https://orcid.org/0000-0002-2286-3216"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho-Taek Joo","raw_affiliation_strings":["School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea","School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea"],"raw_orcid":"https://orcid.org/0000-0002-2286-3216","affiliations":[{"raw_affiliation_string":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030760372","display_name":"In-Chang Baek","orcid":"https://orcid.org/0000-0002-9409-9253"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In-Chang Baek","raw_affiliation_strings":["AI Graduate School, Gwangju Institute of Science and Technology, Gwangju, South Korea","AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9409-9253","affiliations":[{"raw_affiliation_string":"AI Graduate School, Gwangju Institute of Science and Technology, Gwangju, South Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076055880","display_name":"Kyung-Joong Kim","orcid":"https://orcid.org/0000-0002-7732-0817"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyung-Joong Kim","raw_affiliation_strings":["School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea","School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea and AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7732-0817","affiliations":[{"raw_affiliation_string":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea and AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005 South Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5124,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71240181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"57369","last_page":"57382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9115354418754578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.765622615814209},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6842539310455322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6524840593338013},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.6165976524353027},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5718389749526978},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5701102018356323},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5070335865020752},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4505860209465027},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.44023260474205017},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39316385984420776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38353532552719116},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.25558435916900635},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.24621424078941345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13748562335968018}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9115354418754578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765622615814209},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6842539310455322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6524840593338013},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.6165976524353027},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5718389749526978},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5701102018356323},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5070335865020752},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4505860209465027},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.44023260474205017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39316385984420776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38353532552719116},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25558435916900635},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.24621424078941345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13748562335968018},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3178194","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3178194","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09782432.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:63d4ca3c14204659957acaebb1390161","is_oa":true,"landing_page_url":"https://doaj.org/article/63d4ca3c14204659957acaebb1390161","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 57369-57382 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3178194","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3178194","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09782432.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G5344988298","display_name":null,"funder_award_id":"2021R1A4A1030075","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285264760.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2605102758","https://openalex.org/W2749807327","https://openalex.org/W2766447205","https://openalex.org/W2781585732","https://openalex.org/W2967681060","https://openalex.org/W2979211489","https://openalex.org/W2990138404","https://openalex.org/W2991355586","https://openalex.org/W2997103132","https://openalex.org/W3021708257","https://openalex.org/W3022566517","https://openalex.org/W3115293622","https://openalex.org/W4287756699","https://openalex.org/W4287811291","https://openalex.org/W6631190155","https://openalex.org/W6743756900","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6757469721","https://openalex.org/W6768617876","https://openalex.org/W6771270455","https://openalex.org/W6771740491","https://openalex.org/W6771750343","https://openalex.org/W6774583691","https://openalex.org/W6775634482","https://openalex.org/W6776438516","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6779265984","https://openalex.org/W6780159193","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W4225619808","https://openalex.org/W4400438570","https://openalex.org/W4376223516","https://openalex.org/W4226042081","https://openalex.org/W4388926065","https://openalex.org/W4284974072","https://openalex.org/W4308935744","https://openalex.org/W4362599051"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,78],"(RL)":[3],"is":[4,67,109,209],"applied":[5],"to":[6,13,48,61,69,92,111,145,158],"fixed":[7,25],"datasets":[8],"of":[9,88,96,105,115,162,185,192,200],"logged":[10],"interactions":[11],"pertaining":[12],"actual":[14],"applications":[15],"in":[16,33,142,148,174,189],"healthcare,":[17],"autonomous":[18],"vehicles,":[19],"and":[20,24,52,74,129],"robotics.":[21],"In":[22],"limited":[23],"dataset":[26],"settings,":[27],"data":[28,42,140],"augmentation":[29,43],"can":[30,217],"be":[31,218],"beneficial":[32],"developing":[34],"better":[35],"policies.":[36],"Several":[37],"online":[38],"RL":[39,72,165,213],"methods":[40],"for":[41],"have":[44],"recently":[45],"been":[46],"utilized":[47],"enhance":[49,70],"sampling":[50],"efficiency":[51],"generalization.":[53],"Here,":[54],"a":[55,89,181],"novel,":[56],"simple":[57],"data-augmentation":[58],"technique":[59],"referred":[60],"as":[62,126,132],"Swapping":[63],"Target":[64],"Q-Value":[65],"(SQV)":[66],"introduced":[68],"offline":[71,164,212],"algorithms":[73],"enable":[75],"robust":[76],"pixel-based":[77],"without":[79],"auxiliary":[80],"loss.":[81],"Our":[82],"method":[83,122,168,187],"matches":[84],"the":[85,93,97,102,106,112,116,127,136,143,149,160,163,175,183,210],"current":[86,103],"Q-value":[87,95,104,114],"transformed":[90,118],"image":[91,108],"target":[94,113],"next":[98,117],"original":[99,107],"image,":[100],"whereby":[101],"matched":[110],"image.":[119],"The":[120,167,215],"proposed":[121],"considers":[123],"similar":[124,146],"states":[125,131,147],"same":[128],"different":[130],"more":[133],"distinct.":[134],"Furthermore,":[135],"approach":[137],"ties":[138],"unseen":[139],"(lacking":[141],"dataset)":[144],"seen":[150],"data.":[151],"After":[152],"training,":[153],"these":[154],"effects":[155],"were":[156],"observed":[157],"increase":[159],"performance":[161,184,198],"algorithm.":[166],"was":[169],"tested":[170],"on":[171],"23":[172,193],"games":[173],"Atari":[176],"2600":[177],"game":[178],"domain.":[179],"As":[180],"result,":[182],"our":[186],"improved":[188],"18":[190],"out":[191],"games,":[194],"with":[195,203],"an":[196],"average":[197],"improvement":[199],"144%":[201],"compared":[202],"batch-constrained":[204],"deep":[205],"Q-learning":[206],"(BCQ),":[207],"which":[208],"latest":[211],"method.":[214],"implementation":[216],"found":[219],"at":[220],"https://github.com/hotaekjoo/SQV.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}