{"id":"https://openalex.org/W2790331160","doi":"https://doi.org/10.1109/iros.2018.8594018","title":"Synthesizing Neural Network Controllers with Probabilistic Model-Based Reinforcement Learning","display_name":"Synthesizing Neural Network Controllers with Probabilistic Model-Based Reinforcement Learning","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2790331160","doi":"https://doi.org/10.1109/iros.2018.8594018","mag":"2790331160"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/1803.02291","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007491151","display_name":"Juan Camilo Gamboa Higuera","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Juan Camilo Gamboa Higuera","raw_affiliation_strings":["Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109496264","display_name":"David Meger","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Meger","raw_affiliation_strings":["Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075441381","display_name":"Gregory Dudek","orcid":"https://orcid.org/0000-0001-5040-4925"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gregory Dudek","raw_affiliation_strings":["Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007491151"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.1692,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57413463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2538","last_page":"2544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9656999707221985,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9656999707221985,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9265999794006348,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9205999970436096,"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":0.7685532569885254},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7522279024124146},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.637396514415741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6373727321624756},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6077172756195068},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5589573979377747},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5298264622688293},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.49657613039016724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46830689907073975},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4271710515022278}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7685532569885254},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522279024124146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.637396514415741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373727321624756},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6077172756195068},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5589573979377747},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5298264622688293},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49657613039016724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46830689907073975},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4271710515022278},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros.2018.8594018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.02291","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.02291","pdf_url":"https://arxiv.org/pdf/1803.02291","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2790331160","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.02291","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":"doi:10.48550/arxiv.1803.02291","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.02291","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.02291","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.02291","pdf_url":"https://arxiv.org/pdf/1803.02291","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.46000000834465027,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2790331160.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1511334422","https://openalex.org/W1964946446","https://openalex.org/W1997543377","https://openalex.org/W2018705428","https://openalex.org/W2117629901","https://openalex.org/W2157017986","https://openalex.org/W2170912685","https://openalex.org/W2604883922","https://openalex.org/W4241649586","https://openalex.org/W6607786297","https://openalex.org/W6617145748","https://openalex.org/W6631190155","https://openalex.org/W6635067934","https://openalex.org/W6635991215","https://openalex.org/W6638545294","https://openalex.org/W6638836233","https://openalex.org/W6639949747","https://openalex.org/W6674330103","https://openalex.org/W6678367057","https://openalex.org/W6679524480","https://openalex.org/W6684488266","https://openalex.org/W6684921986","https://openalex.org/W6685331716","https://openalex.org/W6696324988","https://openalex.org/W6732814185","https://openalex.org/W6737757103","https://openalex.org/W6738735913","https://openalex.org/W6743806954","https://openalex.org/W6744321392"],"related_works":["https://openalex.org/W2963221646","https://openalex.org/W2953374008","https://openalex.org/W3197109973","https://openalex.org/W1580754821","https://openalex.org/W404990318","https://openalex.org/W2200938002","https://openalex.org/W3193175143","https://openalex.org/W2161570498","https://openalex.org/W45863315","https://openalex.org/W2134116306","https://openalex.org/W2320680215","https://openalex.org/W2043787972","https://openalex.org/W3010449548","https://openalex.org/W1536863689","https://openalex.org/W2766710212","https://openalex.org/W1575271904","https://openalex.org/W2109143310","https://openalex.org/W2625138576","https://openalex.org/W2464772092","https://openalex.org/W2149570255"],"abstract_inverted_index":{"We":[0,56,81],"present":[1],"an":[2],"algorithm":[3,14,45,116,134],"for":[4,10,117,121,135],"rapidly":[5],"learning":[6,19,118],"neural":[7,34,60,78,106],"network":[8,35,61,79,107],"policies":[9],"robotics":[11],"systems.":[12],"The":[13],"follows":[15],"the":[16,112,115,130,133,138],"model-based":[17,44],"reinforcement":[18],"paradigm":[20],"and":[21,27,51,140],"improves":[22],"upon":[23],"existing":[24],"algorithms:":[25],"PILeO":[26],"a":[28,43,59,86,122],"sample-based":[29],"version":[30],"of":[31,76,88,98,114,132],"PILeo":[32],"with":[33,67,96],"dynamics":[36,62],"(Deep-PILeO).":[37],"To":[38],"improve":[39],"convergence,":[40],"we":[41,110],"propose":[42,57],"that":[46,93,97],"uses":[47],"fixed":[48],"random":[49],"numbers":[50],"clips":[52],"gradients":[53],"during":[54],"optimization.":[55],"training":[58],"model":[63],"using":[64],"variational":[65],"dropout":[66],"truncated":[68],"Log-Normal":[69],"noise.":[70],"These":[71],"improvements":[72],"enable":[73],"data-efficient":[74],"synthesis":[75],"complex":[77,105,145],"policies.":[80],"test":[82],"our":[83],"approach":[84],"on":[85],"variety":[87],"benchmark":[89],"tasks,":[90],"demonstrating":[91],"data-efficiency":[92],"is":[94],"competitive":[95],"PILeO,":[99],"while":[100],"being":[101],"able":[102],"to":[103],"optimize":[104],"controllers.":[108],"Finally,":[109],"assess":[111],"performance":[113],"motor":[119],"controllers":[120],"six":[123],"legged":[124],"autonomous":[125],"underwater":[126],"vehicle.":[127],"This":[128],"demonstrates":[129],"potential":[131],"scaling":[136],"up":[137],"dimensionality":[139],"dataset":[141],"sizes,":[142],"in":[143],"more":[144],"tasks.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-10-06T00:00:00"}