{"id":"https://openalex.org/W2987388938","doi":"https://doi.org/10.1109/iros40897.2019.8967896","title":"Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient","display_name":"Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2987388938","doi":"https://doi.org/10.1109/iros40897.2019.8967896","mag":"2987388938"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.06833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040226194","display_name":"Kevin Sebastian Luck","orcid":"https://orcid.org/0000-0003-2228-203X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Sebastian Luck","raw_affiliation_strings":["Arizona State University,Interactive Robotics Lab,Tempe,AZ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Interactive Robotics Lab,Tempe,AZ,USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032877928","display_name":"Mel Vecer\u00edk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mel Vecerik","raw_affiliation_strings":["Google DeepMind,London,UK","[Google DeepMind, London, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,UK","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]},{"raw_affiliation_string":"[Google DeepMind, London, UK]","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048668442","display_name":"Simon Stepputtis","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Stepputtis","raw_affiliation_strings":["Arizona State University,Interactive Robotics Lab,Tempe,AZ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Interactive Robotics Lab,Tempe,AZ,USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024068845","display_name":"Heni Ben Amor","orcid":"https://orcid.org/0000-0002-9896-8217"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heni Ben Amor","raw_affiliation_strings":["Arizona State University,Interactive Robotics Lab,Tempe,AZ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Interactive Robotics Lab,Tempe,AZ,USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077984643","display_name":"Jonathan Scholz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Scholz","raw_affiliation_strings":["Google DeepMind,London,UK","[Google DeepMind, London, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,London,UK","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]},{"raw_affiliation_string":"[Google DeepMind, London, UK]","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5784,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76584862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3704","last_page":"3711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9900000095367432,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8370281457901001},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7308346033096313},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6694433689117432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.651982843875885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5792144536972046},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5568298101425171},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5214849710464478},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48914745450019836},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4648173451423645},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4550027847290039},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.4416182041168213},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.42379915714263916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2070692479610443},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09437203407287598}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8370281457901001},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7308346033096313},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6694433689117432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.651982843875885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792144536972046},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5568298101425171},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5214849710464478},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48914745450019836},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4648173451423645},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4550027847290039},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.4416182041168213},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.42379915714263916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2070692479610443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09437203407287598},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"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/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros40897.2019.8967896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.06833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.06833","pdf_url":"https://arxiv.org/pdf/1911.06833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1911.06833","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.06833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2987388938","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.06833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.06833","pdf_url":"https://arxiv.org/pdf/1911.06833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2987388938.pdf","grobid_xml":"https://content.openalex.org/works/W2987388938.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W2005126631","https://openalex.org/W2016773334","https://openalex.org/W2017957151","https://openalex.org/W2167117957","https://openalex.org/W2173248099","https://openalex.org/W2561776174","https://openalex.org/W2614839826","https://openalex.org/W2622196250","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2769112066","https://openalex.org/W2775490434","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2795756076","https://openalex.org/W2805762288","https://openalex.org/W2810677299","https://openalex.org/W2869375357","https://openalex.org/W2891423421","https://openalex.org/W2894383471","https://openalex.org/W2913871909","https://openalex.org/W2913938871","https://openalex.org/W2962872206","https://openalex.org/W2963082139","https://openalex.org/W2963523627","https://openalex.org/W2968116426","https://openalex.org/W6622487243","https://openalex.org/W6639949747","https://openalex.org/W6653435097","https://openalex.org/W6684921986","https://openalex.org/W6730641667","https://openalex.org/W6741002519","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6750409132","https://openalex.org/W6751494529","https://openalex.org/W6752818208","https://openalex.org/W6754605227","https://openalex.org/W6755561334"],"related_works":["https://openalex.org/W3003910700","https://openalex.org/W3129139000","https://openalex.org/W2969218738","https://openalex.org/W3129131971","https://openalex.org/W2806098286","https://openalex.org/W3002765113","https://openalex.org/W2894422428","https://openalex.org/W3204553045","https://openalex.org/W3093511015","https://openalex.org/W3123748881","https://openalex.org/W2752954743","https://openalex.org/W2099270968","https://openalex.org/W3173335889","https://openalex.org/W2963864421","https://openalex.org/W2548277951","https://openalex.org/W2924656332","https://openalex.org/W2145957964","https://openalex.org/W2963179943","https://openalex.org/W2945529113","https://openalex.org/W1824285808"],"abstract_inverted_index":{"Model-free":[0],"reinforcement":[1,86],"learning":[2,87],"algorithms":[3],"such":[4],"as":[5,61,155],"Deep":[6,38],"Deterministic":[7,39],"Policy":[8,40],"Gradient":[9,41],"(DDPG)":[10],"often":[11],"require":[12],"additional":[13],"exploration":[14,36,112],"strategies,":[15],"especially":[16],"if":[17],"the":[18,27,73,84,90,99,103,107,110,115,133,158],"actor":[19],"is":[20,55,141],"of":[21,29,53,65],"deterministic":[22],"nature.":[23],"This":[24,76],"work":[25],"evaluates":[26],"use":[28,64],"model-based":[30],"trajectory":[31,92,95],"optimization":[32],"methods":[33,119],"used":[34],"for":[35],"in":[37,128,132],"when":[42],"trained":[43,142],"on":[44,122],"a":[45,58,66,80,138],"latent":[46,91],"image":[47],"embedding.":[48],"In":[49,136],"addition,":[50],"an":[51,145],"extension":[52],"DDPG":[54],"derived":[56],"using":[57],"value":[59],"function":[60],"critic,":[62],"making":[63],"learned":[67,101],"deep":[68,85],"dynamics":[69],"model":[70],"to":[71,79,143],"compute":[72],"policy":[74],"gradient.":[75],"approach":[77],"leads":[78],"symbiotic":[81],"relationship":[82],"between":[83],"algorithm":[88,105],"and":[89,106,130,153],"optimizer.":[93],"The":[94,117],"optimizer":[96],"benefits":[97],"from":[98,109,157],"critic":[100],"by":[102,114],"RL":[104],"latter":[108],"enhanced":[111],"generated":[113],"planner.":[116],"developed":[118],"are":[120],"evaluated":[121],"two":[123],"continuous":[124],"control":[125],"tasks,":[126],"one":[127,131],"simulation":[129],"real":[134],"world.":[135],"particular,":[137],"Baxter":[139],"robot":[140],"perform":[144],"insertion":[146],"task,":[147],"while":[148],"only":[149],"receiving":[150],"sparse":[151],"rewards":[152],"images":[154],"observations":[156],"environment.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}