{"id":"https://openalex.org/W4285154955","doi":"https://doi.org/10.1109/access.2022.3182107","title":"Utilizing Skipped Frames in Action Repeats for Improving Sample Efficiency in Reinforcement Learning","display_name":"Utilizing Skipped Frames in Action Repeats for Improving Sample Efficiency in Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285154955","doi":"https://doi.org/10.1109/access.2022.3182107"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3182107","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3182107","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09793636.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/ielx7/6287639/6514899/09793636.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028393159","display_name":"Tung M. Luu","orcid":"https://orcid.org/0000-0001-9488-7463"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Tung M. Luu","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020240470","display_name":"Thanh Nguyen","orcid":"https://orcid.org/0000-0003-3533-4054"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Thanh Nguyen","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059033571","display_name":"Thang Vu","orcid":"https://orcid.org/0000-0003-0486-6349"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Thang Vu","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028393159"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.552,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71538396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":null,"first_page":"64965","last_page":"64975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9851999878883362,"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":0.8215316534042358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686970233917236},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.7362669110298157},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6884371042251587},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6427362561225891},{"id":"https://openalex.org/keywords/de-facto","display_name":"De facto","score":0.5921903848648071},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.591533362865448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5719507932662964},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4631222188472748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45925256609916687},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42331811785697937},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1329580843448639}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8215316534042358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686970233917236},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.7362669110298157},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6884371042251587},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6427362561225891},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.5921903848648071},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.591533362865448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719507932662964},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4631222188472748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45925256609916687},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42331811785697937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1329580843448639},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3182107","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3182107","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09793636.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:e0a58afb59ab4cd8997580262ded111d","is_oa":true,"landing_page_url":"https://doaj.org/article/e0a58afb59ab4cd8997580262ded111d","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 10, Pp 64965-64975 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3182107","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3182107","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09793636.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":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G8566076662","display_name":null,"funder_award_id":"2022-0-00951","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"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285154955.pdf","grobid_xml":"https://content.openalex.org/works/W4285154955.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1522301498","https://openalex.org/W1949804828","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2157864803","https://openalex.org/W2257979135","https://openalex.org/W2292128556","https://openalex.org/W2509374375","https://openalex.org/W2605102581","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2772709170","https://openalex.org/W2913403708","https://openalex.org/W2962847657","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3036619998","https://openalex.org/W4214717370","https://openalex.org/W4288294128","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6683554789","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6720501231","https://openalex.org/W6729556111","https://openalex.org/W6733732937","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6746177919","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6750253780","https://openalex.org/W6756256016","https://openalex.org/W6759008790","https://openalex.org/W6760405395","https://openalex.org/W6765407481","https://openalex.org/W6771217966","https://openalex.org/W6772005887","https://openalex.org/W6774733536","https://openalex.org/W6775634482","https://openalex.org/W6776867236","https://openalex.org/W6780226713","https://openalex.org/W6782858274","https://openalex.org/W6787268631","https://openalex.org/W6787713516","https://openalex.org/W6795704470","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W3123876860","https://openalex.org/W3124172198","https://openalex.org/W2046181650","https://openalex.org/W2142633247"],"abstract_inverted_index":{"Action":[0],"repeat":[1],"has":[2],"become":[3],"the":[4,19,24,38,49,67,76,80,92,95,112,119],"de-facto":[5],"mechanism":[6],"in":[7,46,59],"deep":[8],"reinforcement":[9],"learning":[10],"(RL)":[11],"for":[12,31],"stabilizing":[13],"training":[14,60,71],"and":[15,27,108],"enhancing":[16],"exploration.":[17],"Here,":[18],"action":[20,93],"is":[21,28,73,85,106],"taken":[22],"at":[23,94],"action-decision":[25],"point":[26],"executed":[29],"repeatedly":[30],"a":[32],"designated":[33],"number":[34],"of":[35],"times":[36],"until":[37],"next":[39],"decision":[40],"point.":[41],"Although":[42],"showing":[43],"several":[44],"advantages,":[45],"this":[47],"mechanism,":[48],"intermediate":[50,96],"states":[51,69,97],"which":[52,78],"stem":[53],"from":[54],"repeated":[55],"actions":[56],"are":[57],"discarded":[58,68],"agents,":[61],"causing":[62],"sample":[63],"inefficiency.":[64],"To":[65],"utilize":[66],"as":[70,75],"data":[72],"nontrivial":[74],"action,":[77],"causes":[79],"transition":[81],"between":[82],"these":[83],"states,":[84],"unavailable.":[86],"This":[87],"paper":[88],"proposes":[89],"to":[90],"infer":[91],"via":[98],"an":[99],"inverse":[100],"dynamic":[101],"model.":[102],"The":[103],"proposed":[104,120],"method":[105,121],"simple":[107],"easily":[109],"incorporated":[110],"into":[111],"existing":[113],"off-policy":[114],"RL":[115],"algorithms":[116],"-":[117],"integrating":[118],"with":[122],"SAC":[123],"shows":[124],"consistent":[125],"improvement":[126],"across":[127],"various":[128],"tasks.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}