{"id":"https://openalex.org/W4401567346","doi":"https://doi.org/10.1109/tnnls.2024.3439261","title":"Masked and Inverse Dynamics Modeling for Data-Efficient Reinforcement Learning","display_name":"Masked and Inverse Dynamics Modeling for Data-Efficient Reinforcement Learning","publication_year":2024,"publication_date":"2024-08-14","ids":{"openalex":"https://openalex.org/W4401567346","doi":"https://doi.org/10.1109/tnnls.2024.3439261","pmid":"https://pubmed.ncbi.nlm.nih.gov/39141453"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3439261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3439261","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100360631","display_name":"Young Jae Lee","orcid":"https://orcid.org/0000-0002-1309-0602"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Jae Lee","raw_affiliation_strings":["Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1309-0602","affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347889","display_name":"Jaehoon Kim","orcid":"https://orcid.org/0000-0002-4773-6467"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehoon Kim","raw_affiliation_strings":["Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4773-6467","affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716896","display_name":"Young Joon Park","orcid":"https://orcid.org/0000-0002-3950-3065"},"institutions":[{"id":"https://openalex.org/I4210131320","display_name":"LG (South Korea)","ror":"https://ror.org/03ddh2c27","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210131320"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Joon Park","raw_affiliation_strings":["LG AI Research, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3950-3065","affiliations":[{"raw_affiliation_string":"LG AI Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4210131320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045454868","display_name":"Min Gu Kwak","orcid":"https://orcid.org/0000-0003-0649-9909"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingu Kwak","raw_affiliation_strings":["School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0649-9909","affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058258354","display_name":"Seoung Bum Kim","orcid":"https://orcid.org/0000-0002-2205-8516"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seoung Bum Kim","raw_affiliation_strings":["Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-2205-8516","affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6671,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86176629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"36","issue":"5","first_page":"8814","last_page":"8827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8773000240325928,"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":0.8773000240325928,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.85589998960495,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.8140000104904175,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6126883625984192},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5893547534942627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5551012754440308},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5495681166648865},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5138897895812988},{"id":"https://openalex.org/keywords/inverse-dynamics","display_name":"Inverse dynamics","score":0.4676484763622284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3934956192970276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24755409359931946},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1768789291381836},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15052485466003418},{"id":"https://openalex.org/keywords/classical-mechanics","display_name":"Classical mechanics","score":0.09925669431686401},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06905275583267212},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06410369277000427},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05935254693031311}],"concepts":[{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6126883625984192},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5893547534942627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5551012754440308},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5495681166648865},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5138897895812988},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.4676484763622284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3934956192970276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24755409359931946},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1768789291381836},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15052485466003418},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.09925669431686401},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06905275583267212},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06410369277000427},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05935254693031311},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3439261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3439261","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39141453","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39141453","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2149454052","https://openalex.org/W2150468603","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2787666871","https://openalex.org/W2904246096","https://openalex.org/W2952867909","https://openalex.org/W2963420272","https://openalex.org/W2963523627","https://openalex.org/W3035524453","https://openalex.org/W3093210455","https://openalex.org/W3175558129","https://openalex.org/W3205321526","https://openalex.org/W4252279978","https://openalex.org/W4312346917","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6674884181","https://openalex.org/W6683300800","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6731293529","https://openalex.org/W6740092555","https://openalex.org/W6747387971","https://openalex.org/W6753925943","https://openalex.org/W6755207826","https://openalex.org/W6756256016","https://openalex.org/W6760405395","https://openalex.org/W6765407481","https://openalex.org/W6767737316","https://openalex.org/W6771217966","https://openalex.org/W6776556448","https://openalex.org/W6776867236","https://openalex.org/W6778883912","https://openalex.org/W6780470247","https://openalex.org/W6780730929","https://openalex.org/W6781203905","https://openalex.org/W6782858274","https://openalex.org/W6787268631","https://openalex.org/W6787713516","https://openalex.org/W6790416196","https://openalex.org/W6791000347","https://openalex.org/W6791194670","https://openalex.org/W6796592068","https://openalex.org/W6796761347","https://openalex.org/W6796848067","https://openalex.org/W6799458897","https://openalex.org/W6800570120","https://openalex.org/W6803519892","https://openalex.org/W6810343060","https://openalex.org/W6839256673","https://openalex.org/W6839404800","https://openalex.org/W6839946820","https://openalex.org/W6842654171","https://openalex.org/W6843334904","https://openalex.org/W6846599864","https://openalex.org/W6851949647","https://openalex.org/W6852575923","https://openalex.org/W6853863622"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W400207537","https://openalex.org/W1487930919","https://openalex.org/W1974966543","https://openalex.org/W2550974801","https://openalex.org/W4205272379","https://openalex.org/W2218699221","https://openalex.org/W1519970984","https://openalex.org/W4285133152","https://openalex.org/W2184783674"],"abstract_inverted_index":{"In":[0],"pixel-based":[1],"deep":[2],"reinforcement":[3],"learning":[4,6,39,121],"(DRL),":[5],"representations":[7,47,61,109],"of":[8,13,117],"states":[9],"that":[10,80,122],"change":[11,81],"because":[12],"an":[14,83],"agent's":[15,84],"action":[16],"or":[17,62],"interaction":[18,87],"with":[19,37,82,88,177,210],"the":[20,77,89,129,134,157,165,172],"environment":[21],"poses":[22],"a":[23,118,124,186],"critical":[24],"challenge":[25],"in":[26,56,63,110,133,164],"improving":[27],"data":[28,42,65,222],"efficiency.":[29,223],"Recent":[30],"data-efficient":[31],"DRL":[32,36],"studies":[33],"have":[34,54],"integrated":[35],"self-supervised":[38,119,145],"(SSL)":[40],"and":[41,86,94,103,150,167,206,219],"augmentation":[43,102],"to":[44,74,106,143,189],"learn":[45,76,107],"state":[46,60,175,197],"from":[48],"given":[49],"interactions.":[50,212],"However,":[51],"some":[52],"methods":[53,216],"difficulties":[55],"explicitly":[57,75],"capturing":[58],"evolving":[59,174,196],"selecting":[64],"augmentations":[66],"for":[67,162],"appropriate":[68],"reward":[69],"signals.":[70],"Our":[71,113],"goal":[72],"is":[73,115,226],"inherent":[78],"dynamics":[79,96,152,169,183],"intervention":[85],"environment.":[90],"We":[91,199],"propose":[92],"masked":[93,148,190],"inverse":[95,151,168,182],"modeling":[97,149,155,170,184],"(MIND),":[98],"which":[99,127],"uses":[100,140],"masking":[101],"fewer":[104],"hyperparameters":[105],"agent-controllable":[108],"changing":[111],"states.":[112],"method":[114,193,202],"comprised":[116],"multitask":[120,146],"leverages":[123],"transformer":[125],"architecture,":[126],"captures":[128],"spatiotemporal":[130],"information":[131],"underlying":[132],"highly":[135],"correlated":[136],"consecutive":[137],"frames.":[138],"MIND":[139,213],"two":[141],"tasks":[142],"perform":[144],"learning:":[147],"modeling.":[153],"Masked":[154],"learns":[156,171,195],"static":[158],"visual":[159],"representation":[160,176],"required":[161],"control":[163,208],"state,":[166],"rapidly":[173],"agent":[178],"intervention.":[179],"By":[180],"integrating":[181],"as":[185],"complementary":[187],"component":[188],"modeling,":[191],"our":[192,201],"effectively":[194],"representations.":[198],"evaluate":[200],"by":[203],"using":[204],"discrete":[205],"continuous":[207],"environments":[209],"limited":[211],"outperforms":[214],"previous":[215],"across":[217],"benchmarks":[218],"significantly":[220],"improves":[221],"The":[224],"code":[225],"available":[227],"at":[228],"https://github.com/dudwojae/MIND.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}