{"id":"https://openalex.org/W2966950754","doi":"https://doi.org/10.1109/iros40897.2019.8968584","title":"Learning to Explore in Motion and Interaction Tasks","display_name":"Learning to Explore in Motion and Interaction Tasks","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2966950754","doi":"https://doi.org/10.1109/iros40897.2019.8968584","mag":"2966950754"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968584","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/1908.03731","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032586525","display_name":"Miroslav Bogdanovi\u0107","orcid":"https://orcid.org/0000-0001-7255-7658"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Miroslav Bogdanovic","raw_affiliation_strings":["Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,Tübingen,Germany","Max-Planck-Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,Tübingen,Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Max-Planck-Society","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026007843","display_name":"Ludovic Righetti","orcid":"https://orcid.org/0000-0002-6458-9112"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ludovic Righetti","raw_affiliation_strings":["Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,Tübingen,Germany","Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,T\u00fcbingen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,Tübingen,Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,T\u00fcbingen,Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08887607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2686","last_page":"2692"},"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/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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9879999756813049,"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/computer-science","display_name":"Computer science","score":0.790631890296936},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7765882015228271},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6588784456253052},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6492928862571716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6083375215530396},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5588520765304565},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5452622771263123},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.502072811126709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48381131887435913},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.44632479548454285},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42570269107818604},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41465115547180176},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33851733803749084},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13368088006973267},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07158768177032471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790631890296936},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7765882015228271},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6588784456253052},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6492928862571716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6083375215530396},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5588520765304565},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5452622771263123},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.502072811126709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48381131887435913},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44632479548454285},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42570269107818604},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41465115547180176},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33851733803749084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13368088006973267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07158768177032471},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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":5,"locations":[{"id":"doi:10.1109/iros40897.2019.8968584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968584","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:1908.03731","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03731","pdf_url":"https://arxiv.org/pdf/1908.03731","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":"","raw_type":"text"},{"id":"pmh:oai:pure.mpg.de:item_3247466","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0006-F42B-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1908.03731","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.03731","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":"Preprint"},{"id":"mag:2966950754","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:1908.03731","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03731","pdf_url":"https://arxiv.org/pdf/1908.03731","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966950754.pdf","grobid_xml":"https://content.openalex.org/works/W2966950754.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W130216483","https://openalex.org/W1486707268","https://openalex.org/W1684361744","https://openalex.org/W1810943226","https://openalex.org/W2017957151","https://openalex.org/W2064675550","https://openalex.org/W2136719407","https://openalex.org/W2161697934","https://openalex.org/W2173248099","https://openalex.org/W2534060593","https://openalex.org/W2614839826","https://openalex.org/W2735995851","https://openalex.org/W2736601468","https://openalex.org/W2809256243","https://openalex.org/W2810132790","https://openalex.org/W2911087563","https://openalex.org/W2962943672","https://openalex.org/W2963024489","https://openalex.org/W2963523627","https://openalex.org/W2964118020","https://openalex.org/W4211008118","https://openalex.org/W4250979948","https://openalex.org/W6628902087","https://openalex.org/W6638273328","https://openalex.org/W6683526187","https://openalex.org/W6684921986","https://openalex.org/W6729130418","https://openalex.org/W6739193204","https://openalex.org/W6740879895","https://openalex.org/W6741002519","https://openalex.org/W6748523217","https://openalex.org/W6752603789"],"related_works":["https://openalex.org/W3003653070","https://openalex.org/W2996006200","https://openalex.org/W3111396778","https://openalex.org/W3021105371","https://openalex.org/W2789102901","https://openalex.org/W3135512538","https://openalex.org/W2281096776","https://openalex.org/W3149922422","https://openalex.org/W3138650132","https://openalex.org/W2968556640","https://openalex.org/W2990874363","https://openalex.org/W2915692735","https://openalex.org/W3109409708","https://openalex.org/W3126596751","https://openalex.org/W3203056473","https://openalex.org/W2198225532","https://openalex.org/W3115080916","https://openalex.org/W3167810990","https://openalex.org/W2554830522","https://openalex.org/W1523133203"],"abstract_inverted_index":{"Model":[0],"free":[1],"reinforcement":[2],"learning":[3,76,84,128],"suffers":[4],"from":[5,70],"the":[6,49,52,110,113,121,136],"high":[7],"sampling":[8,23],"complexity":[9],"inherent":[10],"to":[11,27,74,140],"robotic":[12,151],"manipulation":[13],"or":[14],"locomotion":[15],"tasks.":[16,46,78],"Most":[17],"successful":[18],"approaches":[19],"typically":[20],"use":[21],"random":[22],"strategies":[24,88],"which":[25],"leads":[26],"slow":[28],"policy":[29],"convergence.":[30],"In":[31,115],"this":[32],"paper":[33],"we":[34],"present":[35],"a":[36,62,97,101],"novel":[37,90],"approach":[38,80],"for":[39,65,149],"efficient":[40],"exploration":[41,66,87,122],"that":[42,51,120],"leverages":[43],"previously":[44,71],"learned":[45],"We":[47],"exploit":[48],"fact":[50],"same":[53],"system":[54],"is":[55,138],"used":[56],"across":[57],"many":[58],"tasks":[59,73,91,108],"and":[60,105,143],"build":[61],"generative":[63],"model":[64],"based":[67],"on":[68,96],"data":[69],"solved":[72],"improve":[75],"new":[77],"The":[79],"also":[81],"enables":[82],"continuous":[83],"of":[85,103,112],"improved":[86],"as":[89],"are":[92,133],"learned.":[93],"Extensive":[94],"simulations":[95],"robot":[98],"manipulator":[99],"performing":[100],"variety":[102],"motion":[104],"contact":[106],"interaction":[107],"demonstrate":[109],"capabilities":[111],"approach.":[114],"particular,":[116],"our":[117],"experiments":[118],"suggest":[119],"strategy":[123],"can":[124],"more":[125],"than":[126],"double":[127],"speed,":[129],"especially":[130],"when":[131],"rewards":[132],"sparse.":[134],"Moreover,":[135],"algorithm":[137],"robust":[139],"task":[141],"variations":[142],"parameter":[144],"tuning,":[145],"making":[146],"it":[147],"beneficial":[148],"complex":[150],"problems.":[152]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}