{"id":"https://openalex.org/W4390913442","doi":"https://doi.org/10.3390/a17010037","title":"Optimizing Reinforcement Learning Using a Generative Action-Translator Transformer","display_name":"Optimizing Reinforcement Learning Using a Generative Action-Translator Transformer","publication_year":2024,"publication_date":"2024-01-16","ids":{"openalex":"https://openalex.org/W4390913442","doi":"https://doi.org/10.3390/a17010037"},"language":"en","primary_location":{"id":"doi:10.3390/a17010037","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17010037","pdf_url":"https://www.mdpi.com/1999-4893/17/1/37/pdf?version=1705390943","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/17/1/37/pdf?version=1705390943","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100326750","display_name":"Jiaming Li","orcid":"https://orcid.org/0000-0002-7953-7024"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Li","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036466084","display_name":"Ning Xie","orcid":"https://orcid.org/0000-0002-1509-464X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Xie","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101891226","display_name":"Tingting Zhao","orcid":"https://orcid.org/0000-0001-5915-503X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Tingting Zhao","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China","RIKEN Center for Advanced Intelligence Project (AIP), Tokyo 103-0027, Japan"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China","institution_ids":["https://openalex.org/I132369690"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP), Tokyo 103-0027, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036466084"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.3356,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60283956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"17","issue":"1","first_page":"37","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T10260","display_name":"Software Engineering Research","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.973800003528595,"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":0.9354144334793091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8096306324005127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6808141469955444},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6076204180717468},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5938436985015869},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5374477505683899},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4646531939506531},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4236873984336853},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2273411750793457},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08562964200973511}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9354144334793091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8096306324005127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6808141469955444},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6076204180717468},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5938436985015869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5374477505683899},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4646531939506531},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4236873984336853},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2273411750793457},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08562964200973511},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a17010037","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17010037","pdf_url":"https://www.mdpi.com/1999-4893/17/1/37/pdf?version=1705390943","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a59ae43d8429407dbdf8bd10e9ed5e97","is_oa":true,"landing_page_url":"https://doaj.org/article/a59ae43d8429407dbdf8bd10e9ed5e97","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":"Algorithms, Vol 17, Iss 1, p 37 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a17010037","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17010037","pdf_url":"https://www.mdpi.com/1999-4893/17/1/37/pdf?version=1705390943","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G1088547498","display_name":null,"funder_award_id":"61976156","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G160128092","display_name":null,"funder_award_id":"2019-YF08-00285-GX","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G1943486550","display_name":null,"funder_award_id":"SCITLAB-30005","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5476986862","display_name":null,"funder_award_id":"61976156","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6389407352","display_name":null,"funder_award_id":"2019-YF08-00285-GX","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6717149698","display_name":null,"funder_award_id":"2022YFB3104600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7635801005","display_name":null,"funder_award_id":"SCITLAB-30005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8193518817","display_name":null,"funder_award_id":"61976156","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G8280590939","display_name":null,"funder_award_id":"2019-YF08-00285-GX","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G879429020","display_name":null,"funder_award_id":"2022YFB3104600","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8945321275","display_name":null,"funder_award_id":"2022YFB3104600","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G946550729","display_name":null,"funder_award_id":"SCITLAB-30005","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390913442.pdf","grobid_xml":"https://content.openalex.org/works/W4390913442.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2260756217","https://openalex.org/W2896457183","https://openalex.org/W2911109671","https://openalex.org/W2947150733","https://openalex.org/W2952230511","https://openalex.org/W2962787969","https://openalex.org/W2963608065","https://openalex.org/W2980433389","https://openalex.org/W2991355586","https://openalex.org/W3033324992","https://openalex.org/W3106118243","https://openalex.org/W3169291081","https://openalex.org/W3180915449","https://openalex.org/W4291414411","https://openalex.org/W4360584316","https://openalex.org/W6637967152","https://openalex.org/W6683738474","https://openalex.org/W6747943641","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"with":[3,26,58,214],"the":[4,38,51,71,77,85,101,108,111,131,143,150,159,162,167,178,185,189,193,199,219,226],"rapid":[5],"advancements":[6],"in":[7,68,158,207,218],"Natural":[8],"Language":[9],"Processing":[10],"(NLP)":[11],"technologies,":[12],"large":[13],"models":[14,28,55,250],"have":[15,22],"become":[16],"widespread.":[17],"Traditional":[18],"reinforcement":[19,44,78,97,116,144,200,221,252,259],"learning":[20,79,98,117,145,201,222,260],"algorithms":[21],"also":[23],"started":[24],"experimenting":[25],"language":[27,54,122,194,249],"to":[29,74,90,95,129,182],"optimize":[30],"training.":[31,125],"However,":[32,107],"they":[33],"still":[34],"fundamentally":[35],"rely":[36],"on":[37,225],"Markov":[39],"Decision":[40,64],"Process":[41],"(MDP)":[42],"for":[43,56,124,198,247,257],"learning,":[45,253],"and":[46,136,211,245,251],"do":[47],"not":[48],"fully":[49],"exploit":[50],"advantages":[52],"of":[53,61,103,115,148,166,188],"dealing":[57],"long":[59],"sequences":[60],"problems.":[62],"The":[63],"Transformer":[65,180],"(DT)":[66],"introduced":[67],"2021":[69],"is":[70,128],"initial":[72],"effort":[73],"completely":[75],"transform":[76],"problem":[80],"into":[81,119],"a":[82,120,172],"challenge":[83],"within":[84],"NLP":[86],"domain.":[87],"It":[88],"attempts":[89],"use":[91],"text":[92],"generation":[93],"techniques":[94],"create":[96],"trajectories,":[99],"addressing":[100],"issue":[102],"finding":[104,149],"optimal":[105,151],"trajectories.":[106],"article":[109],"places":[110],"training":[112,146,164],"trajectory":[113],"data":[114],"directly":[118],"basic":[121],"model":[123,176,195,206,231,240],"Its":[126],"aim":[127],"predict":[130,183],"entire":[132],"trajectory,":[133],"encompassing":[134],"state":[135],"reward":[137],"information.":[138],"This":[139,169,191],"approach":[140],"deviates":[141],"from":[142],"objective":[147],"action.":[152],"Furthermore,":[153],"it":[154,213],"generates":[155],"redundant":[156],"information":[157],"output,":[160],"impacting":[161],"final":[163],"effectiveness":[165],"agent.":[168,190],"paper":[170],"proposes":[171],"more":[173,196],"reasonable":[174],"network":[175],"structure,":[177],"Action-Translator":[179],"(ATT),":[181],"only":[184],"next":[186],"action":[187],"makes":[192],"interpretable":[197],"problem.":[202],"We":[203,235],"test":[204],"our":[205,230],"simulated":[208],"gaming":[209],"scenarios":[210],"compare":[212],"current":[215],"mainstream":[216],"methods":[217],"offline":[220,258],"field.":[223],"Based":[224],"presented":[227],"experimental":[228],"results,":[229],"demonstrates":[232],"superior":[233],"performance.":[234],"hope":[236],"that":[237],"introducing":[238],"this":[239],"will":[241],"inspire":[242],"new":[243],"ideas":[244],"solutions":[246],"combining":[248],"providing":[254],"fresh":[255],"perspectives":[256],"research.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}
