{"id":"https://openalex.org/W3105267388","doi":"https://doi.org/10.1109/icra48506.2021.9560897","title":"Reward Conditioned Neural Movement Primitives for Population-Based Variational Policy Optimization","display_name":"Reward Conditioned Neural Movement Primitives for Population-Based Variational Policy Optimization","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3105267388","doi":"https://doi.org/10.1109/icra48506.2021.9560897","mag":"3105267388"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/2011.04282","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027287625","display_name":"Mete Tuluhan Akbulut","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"M. Tuluhan Akbulut","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Turkey","Bogazici University, Dept. of Computer Engineering, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bogazici University, Dept. of Computer Engineering, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023874807","display_name":"Utku Bozdo\u011fan","orcid":"https://orcid.org/0000-0002-8912-9446"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Utku Bozdogan","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Turkey","Bogazici University, Dept. of Computer Engineering, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bogazici University, Dept. of Computer Engineering, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023501802","display_name":"Ahmet E. Tekden","orcid":"https://orcid.org/0000-0002-1272-0756"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ahmet Tekden","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Turkey","Bogazici University, Dept. of Computer Engineering, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bogazici University, Dept. of Computer Engineering, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048165304","display_name":"Emre U\u011fur","orcid":"https://orcid.org/0000-0001-9597-2731"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emre Ugur","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Turkey","Bogazici University, Dept. of Computer Engineering, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bogazici University, Dept. of Computer Engineering, Turkey","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027287625"],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01014496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10808","last_page":"10814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9426000118255615,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9394999742507935,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6465179324150085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6403248906135559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6130614876747131},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5549114346504211},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5457708835601807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.540144145488739},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5385301113128662},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.53279048204422},{"id":"https://openalex.org/keywords/crossover","display_name":"Crossover","score":0.49504032731056213},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4948572516441345},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4946705996990204},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4851554036140442},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4480769634246826},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.41053009033203125},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.18798381090164185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17906799912452698}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6465179324150085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6403248906135559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6130614876747131},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5549114346504211},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5457708835601807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.540144145488739},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5385301113128662},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.53279048204422},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.49504032731056213},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4948572516441345},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4946705996990204},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4851554036140442},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4480769634246826},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.41053009033203125},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.18798381090164185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17906799912452698},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icra48506.2021.9560897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.04282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.04282","pdf_url":"https://arxiv.org/pdf/2011.04282","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3105267388","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.04282","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:zenodo.org:4661846","is_oa":true,"landing_page_url":"https://zenodo.org/record/4661846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2011.04282","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.04282","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5281/zenodo.4661845","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4661845","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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-journal"},{"id":"doi:10.5281/zenodo.4661846","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4661846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.04282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.04282","pdf_url":"https://arxiv.org/pdf/2011.04282","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3105267388.pdf","grobid_xml":"https://content.openalex.org/works/W3105267388.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W135283623","https://openalex.org/W1499669280","https://openalex.org/W1608391772","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W2095671661","https://openalex.org/W2100993276","https://openalex.org/W2136719407","https://openalex.org/W2225156818","https://openalex.org/W2569181534","https://openalex.org/W2601477941","https://openalex.org/W2788862220","https://openalex.org/W2908984811","https://openalex.org/W2942608247","https://openalex.org/W2947017371","https://openalex.org/W2963411833","https://openalex.org/W2965567119","https://openalex.org/W2967355195","https://openalex.org/W2972141908","https://openalex.org/W3003570760","https://openalex.org/W3086642896","https://openalex.org/W4206566734","https://openalex.org/W6680971464","https://openalex.org/W6687045409","https://openalex.org/W6711952718","https://openalex.org/W6720208624","https://openalex.org/W6735641298","https://openalex.org/W6744627333","https://openalex.org/W6746622358","https://openalex.org/W6747092830","https://openalex.org/W6750138292","https://openalex.org/W6752040014","https://openalex.org/W6752968661","https://openalex.org/W6754364265","https://openalex.org/W6755459763","https://openalex.org/W6755903938","https://openalex.org/W6764352956","https://openalex.org/W6764969207","https://openalex.org/W6770887232","https://openalex.org/W6778051727","https://openalex.org/W6783988487","https://openalex.org/W6786332875"],"related_works":["https://openalex.org/W3207043744","https://openalex.org/W3101805180","https://openalex.org/W3098951764","https://openalex.org/W3005829072","https://openalex.org/W3139073295","https://openalex.org/W2158969944","https://openalex.org/W3196776285","https://openalex.org/W2963179943","https://openalex.org/W3091628900","https://openalex.org/W2949352476","https://openalex.org/W3152815381","https://openalex.org/W3206843203","https://openalex.org/W2913350117","https://openalex.org/W3042593733","https://openalex.org/W2786663522","https://openalex.org/W2181849516","https://openalex.org/W3179491945","https://openalex.org/W3209253128","https://openalex.org/W2896288931","https://openalex.org/W3119025780"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,18,46,90,96,155,179],"study":[4],"the":[5,32,35,62,83,124,129,135,143,191],"reward-based":[6],"policy":[7],"exploration":[8],"problem":[9],"in":[10,23,100,123,142],"a":[11,48,92,102,116,147,180],"supervised":[12],"learning":[13,171,186],"approach":[14],"and":[15,27,60,114,173],"enable":[16],"robots":[17],"form":[19],"complex":[20],"movement":[21],"trajectories":[22,64,74,99,105],"challenging":[24],"reward":[25,80,84,144],"settings":[26],"search":[28],"spaces.":[29],"For":[30],"this,":[31],"experience":[33],"of":[34,104,128,134,149,182,194],"robot,":[36],"which":[37,120],"can":[38,70],"be":[39],"bootstrapped":[40],"from":[41,56,78,111],"demonstrated":[42],"trajectories,":[43],"is":[44,88,121],"used":[45,89],"train":[47],"novel":[49,117],"Neural":[50],"Processes-based":[51],"deep":[52],"network":[53],"that":[54,137,151,166],"samples":[55],"its":[57],"latent":[58,94,126],"space":[59,95,127],"generates":[61],"required":[63],"given":[65,106],"desired":[66],"rewards.":[67,108],"Our":[68],"framework":[69],"generate":[71],"progressively":[72],"improved":[73],"by":[75],"sampling":[76],"them":[77],"high":[79],"landscapes,":[81],"increasing":[82],"gradually.":[85],"Variational":[86],"inference":[87],"create":[91],"stochastic":[93],"sample":[97,176],"varying":[98],"generating":[101],"population":[103],"target":[107],"We":[109],"benefit":[110],"Evolutionary":[112],"Strategies":[113],"propose":[115],"crossover":[118],"operation,":[119],"applied":[122],"self-organized":[125],"individual":[130],"policies,":[131],"allowing":[132],"blending":[133],"individuals":[136],"might":[138],"address":[139],"different":[140],"factors":[141],"function.":[145],"Using":[146],"number":[148,181],"tasks":[150],"require":[152],"sequential":[153],"reaching":[154],"multiple":[156],"points":[157],"or":[158],"passing":[159],"through":[160,197],"gaps":[161],"between":[162],"objects,":[163],"we":[164,189],"showed":[165],"our":[167,195],"method":[168,196],"provides":[169],"stable":[170],"progress":[172],"significantly":[174],"higher":[175],"efficiency":[177],"compared":[178],"state-of-the-art":[183],"robotic":[184],"reinforcement":[185],"methods.":[187],"Finally,":[188],"show":[190],"real-world":[192],"suitability":[193],"real":[198],"robot":[199],"execution":[200],"involving":[201],"obstacle":[202],"avoidance.":[203]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}