{"id":"https://openalex.org/W4285179996","doi":"https://doi.org/10.1109/lra.2022.3186494","title":"Efficient Spatiotemporal Transformer for Robotic Reinforcement Learning","display_name":"Efficient Spatiotemporal Transformer for Robotic Reinforcement Learning","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4285179996","doi":"https://doi.org/10.1109/lra.2022.3186494"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3186494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3186494","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5041434096","display_name":"Yiming Yang","orcid":"https://orcid.org/0000-0003-1359-0364"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Yang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1359-0364","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684094","display_name":"Dengpeng Xing","orcid":"https://orcid.org/0000-0002-8251-9118"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengpeng Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8251-9118","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1111-1529","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3873,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84167162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"3","first_page":"7982","last_page":"7989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9685999751091003,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.776233434677124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7678144574165344},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6549205780029297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6242156624794006},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6034613251686096},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5786367654800415},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5314003229141235},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5151854753494263},{"id":"https://openalex.org/keywords/operability","display_name":"Operability","score":0.4136126935482025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40862470865249634},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2789326310157776},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.22997775673866272},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.21214497089385986},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13720813393592834},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07475638389587402}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.776233434677124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678144574165344},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6549205780029297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6242156624794006},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6034613251686096},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5786367654800415},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5314003229141235},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5151854753494263},{"id":"https://openalex.org/C126231374","wikidata":"https://www.wikidata.org/wiki/Q1061298","display_name":"Operability","level":2,"score":0.4136126935482025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40862470865249634},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2789326310157776},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.22997775673866272},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.21214497089385986},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13720813393592834},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07475638389587402},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3186494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3186494","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4102930997","display_name":null,"funder_award_id":"62073324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1662842982","https://openalex.org/W2158782408","https://openalex.org/W2736601468","https://openalex.org/W2749604329","https://openalex.org/W2805516822","https://openalex.org/W2903683378","https://openalex.org/W2911549659","https://openalex.org/W2960567166","https://openalex.org/W2982437637","https://openalex.org/W2990747716","https://openalex.org/W2997896361","https://openalex.org/W3000386982","https://openalex.org/W3020831056","https://openalex.org/W3089482831","https://openalex.org/W3113067059","https://openalex.org/W3127352841","https://openalex.org/W3139848350","https://openalex.org/W3169291081","https://openalex.org/W3185826690","https://openalex.org/W3205898195","https://openalex.org/W4226088469","https://openalex.org/W4287078276","https://openalex.org/W4287126489","https://openalex.org/W4292779060","https://openalex.org/W4298857966","https://openalex.org/W4362590704","https://openalex.org/W6637967152","https://openalex.org/W6682864246","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6751796012","https://openalex.org/W6757184387","https://openalex.org/W6764969207","https://openalex.org/W6768810269","https://openalex.org/W6769673253","https://openalex.org/W6773017188","https://openalex.org/W6778883912","https://openalex.org/W6779282036","https://openalex.org/W6779879114","https://openalex.org/W6780559895","https://openalex.org/W6784313279","https://openalex.org/W6792417942","https://openalex.org/W6796289742","https://openalex.org/W6796602679","https://openalex.org/W6798316476","https://openalex.org/W6798613634","https://openalex.org/W6804244202"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W1985560493","https://openalex.org/W2294884454","https://openalex.org/W2937181779"],"abstract_inverted_index":{"Intense":[0],"spatiotemporal":[1,62,87,103],"coupling":[2,11,43],"states":[3,165],"frequently":[4],"appear":[5],"in":[6,16,48,74,105],"robotic":[7,49,76],"tasks,":[8,179],"and":[9,53,127,154,167,180],"this":[10,42,80,93],"enriches":[12],"the":[13,29,57,67,70,96,100,117,121,125,128,132,152,161,173],"information":[14,27,104,140],"encapsulated":[15],"each":[17,108],"state.":[18,134],"Taking":[19],"advantage":[20],"of":[21,61,66,69,124,157,163],"historical":[22],"observations":[23],"can":[24],"provide":[25],"more":[26],"about":[28],"robot,":[30],"especially":[31],"for":[32],"partially":[33],"observable":[34],"Markov":[35],"decision":[36],"processes.":[37],"How":[38],"to":[39,98,119,130,142],"deal":[40],"with":[41,102],"remains":[44],"a":[45],"challenging":[46],"issue":[47],"reinforcement":[50],"learning":[51,75],"(RL),":[52],"we":[54,82,111],"allege":[55],"that":[56],"imbalanced":[58],"processing":[59],"capability":[60],"details":[63],"is":[64,95],"one":[65],"bottlenecks":[68],"vanilla":[71],"transformer":[72,88,101],"model":[73],"policies.":[77],"To":[78,90],"address":[79],"problem,":[81],"novelly":[83],"propose":[84],"an":[85],"efficient":[86],"structure.":[89],"our":[91],"knowledge,":[92],"work":[94],"first":[97,118],"improve":[99],"RL.":[106,186],"In":[107],"attention":[109,114],"block,":[110],"sequentially":[112],"execute":[113],"computation":[115,156],"twice:":[116],"process":[120],"temporal":[122],"sequence":[123],"input":[126,136],"latter":[129],"manage":[131],"spatial":[133],"This":[135],"reconstruction":[137],"enables":[138],"sufficient":[139],"extraction":[141],"promote":[143],"data":[144],"efficiency.":[145],"We":[146,171],"also":[147],"add":[148],"correlation":[149],"encoding":[150],"into":[151],"query":[153],"key":[155],"multi-head":[158],"attention,":[159],"providing":[160],"operability":[162],"associating":[164],"between":[166],"within":[168],"time":[169],"steps.":[170],"evaluate":[172],"proposed":[174],"approach":[175],"on":[176],"several":[177],"robot":[178],"it":[181],"outperforms":[182],"state-of-the-art":[183],"transformer-based":[184],"online":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}