{"id":"https://openalex.org/W2592538810","doi":"https://doi.org/10.1109/iros.2017.8206046","title":"Deep predictive policy training using reinforcement learning","display_name":"Deep predictive policy training using reinforcement learning","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2592538810","doi":"https://doi.org/10.1109/iros.2017.8206046","mag":"2592538810"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8206046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038342432","display_name":"Ali Ghadirzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ali Ghadirzadeh","raw_affiliation_strings":["CSC, KTH Royal Institute of Technology, Stockholm, Sweden","Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054834085","display_name":"Atsuto Maki","orcid":"https://orcid.org/0000-0002-4266-6746"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Atsuto Maki","raw_affiliation_strings":["CSC, KTH Royal Institute of Technology, Stockholm, Sweden","Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["CSC, KTH Royal Institute of Technology, Stockholm, Sweden","Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082269387","display_name":"M\u00e5rten Bj\u00f6rkman","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Marten Bjorkman","raw_affiliation_strings":["CSC, KTH Royal Institute of Technology, Stockholm, Sweden","Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Robotics, Perception and Learning Lab (RPL), CSC, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":8.5823,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.9827122,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2351","last_page":"2358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7449088096618652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7399316430091858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6893501281738281},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5146663784980774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5022265911102295},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48805439472198486},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46815943717956543},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46020716428756714},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44724929332733154},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4447253942489624},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42493322491645813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1491834819316864},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08864554762840271}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7449088096618652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7399316430091858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6893501281738281},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5146663784980774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5022265911102295},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48805439472198486},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46815943717956543},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46020716428756714},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44724929332733154},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4447253942489624},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42493322491645813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1491834819316864},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08864554762840271},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2017.8206046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W834081922","https://openalex.org/W1771410628","https://openalex.org/W1959608418","https://openalex.org/W1968962398","https://openalex.org/W1970890515","https://openalex.org/W1971984830","https://openalex.org/W1977655452","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2104657862","https://openalex.org/W2117494236","https://openalex.org/W2121103318","https://openalex.org/W2123967136","https://openalex.org/W2137376508","https://openalex.org/W2145339207","https://openalex.org/W2155893237","https://openalex.org/W2162977544","https://openalex.org/W2167117957","https://openalex.org/W2173248099","https://openalex.org/W2210018674","https://openalex.org/W2221321873","https://openalex.org/W2231787211","https://openalex.org/W2296691800","https://openalex.org/W2342662072","https://openalex.org/W2443711627","https://openalex.org/W2467604901","https://openalex.org/W2473208550","https://openalex.org/W2529601334","https://openalex.org/W2529658650","https://openalex.org/W2567455162","https://openalex.org/W2591436094","https://openalex.org/W2950094539","https://openalex.org/W2963430173","https://openalex.org/W2963634205","https://openalex.org/W2963641140","https://openalex.org/W2964068416","https://openalex.org/W2964112890","https://openalex.org/W2964161785","https://openalex.org/W3101639353","https://openalex.org/W4205513846","https://openalex.org/W4300311901","https://openalex.org/W4311415873","https://openalex.org/W6623316541","https://openalex.org/W6638018090","https://openalex.org/W6640963894","https://openalex.org/W6653435097","https://openalex.org/W6678157427","https://openalex.org/W6678367057","https://openalex.org/W6683686806","https://openalex.org/W6704571135","https://openalex.org/W6720501231"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W1941703695","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W3131574667","https://openalex.org/W2903025760","https://openalex.org/W2967461658"],"abstract_inverted_index":{"Skilled":[0],"robot":[1,182],"task":[2,128],"learning":[3,145],"is":[4,24,109,124,167],"best":[5],"implemented":[6],"by":[7,147,169],"predictive":[8,22,47,149],"action":[9],"policies":[10,23,150],"due":[11],"to":[12,64,77],"the":[13,36,40,79,120,138,141,165,170],"inherent":[14],"latency":[15],"of":[16,32,39,67,73,93,140,164],"sensorimotor":[17],"processes.":[18],"However,":[19],"training":[20,49,103,148],"such":[21],"challenging":[25],"as":[26,78],"it":[27],"involves":[28],"finding":[29],"a":[30,44,53,65,110,159],"trajectory":[31],"motor":[33,68,96],"activations":[34],"for":[35,126,131,151],"full":[37],"duration":[38],"action.":[41],"We":[42,136],"propose":[43],"data-efficient":[45],"deep":[46,54],"policy":[48,57,81,107,132],"(DPPT)":[50],"framework":[51,146],"with":[52,99,113,184],"neural":[55],"network":[56],"architecture":[58,71,143],"which":[59],"maps":[60,117],"an":[61,91],"image":[62],"observation":[63],"sequence":[66],"activations.":[69],"The":[70,85,106,162],"consists":[72],"three":[74],"sub-networks":[75],"referred":[76],"perception,":[80],"and":[82,87,95,101,144,155],"behavior":[83,88],"super-layers.":[84],"perception":[86],"super-layers":[89],"force":[90],"abstraction":[92],"visual":[94],"data":[97,118],"trained":[98,125,176],"synthetic":[100],"simulated":[102],"samples,":[104],"respectively.":[105],"super-layer":[108],"small":[111],"subnetwork":[112],"fewer":[114],"parameters":[115],"that":[116,172],"in-between":[119],"abstracted":[121],"manifolds.":[122],"It":[123],"each":[127],"using":[129,177],"methods":[130],"search":[133],"reinforcement":[134],"learning.":[135],"demonstrate":[137],"suitability":[139],"proposed":[142],"skilled":[152],"object":[153],"grasping":[154],"ball":[156],"throwing":[157],"on":[158],"PR2":[160],"robot.":[161],"effectiveness":[163],"method":[166],"illustrated":[168],"fact":[171],"these":[173],"tasks":[174],"are":[175],"only":[178],"about":[179],"180":[180],"real":[181],"attempts":[183],"qualitative":[185],"terminal":[186],"rewards.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}