{"id":"https://openalex.org/W1482341360","doi":"https://doi.org/10.1109/icra.2015.7139645","title":"Optimism-driven exploration for nonlinear systems","display_name":"Optimism-driven exploration for nonlinear systems","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1482341360","doi":"https://doi.org/10.1109/icra.2015.7139645","mag":"1482341360"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2015.7139645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7139645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","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/A5001855685","display_name":"Teodor Mihai Moldovan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Teodor Mihai Moldovan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049812527","display_name":"Michael I. Jordan","orcid":"https://orcid.org/0000-0001-8935-817X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I. Jordan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001855685"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":8.1972,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97391662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"303","issue":null,"first_page":"3239","last_page":"3246"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9990000128746033,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9950000047683716,"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":0.7425407767295837},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6609242558479309},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.630476713180542},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6030735373497009},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5437723994255066},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4937795102596283},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4548443555831909},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.4290686249732971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4145916700363159},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3623478412628174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14264529943466187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425407767295837},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6609242558479309},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.630476713180542},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6030735373497009},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5437723994255066},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4937795102596283},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4548443555831909},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.4290686249732971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4145916700363159},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3623478412628174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14264529943466187},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2015.7139645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7139645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W53582479","https://openalex.org/W596064430","https://openalex.org/W1496720559","https://openalex.org/W1556500232","https://openalex.org/W1977655452","https://openalex.org/W1998534269","https://openalex.org/W2003132288","https://openalex.org/W2012587148","https://openalex.org/W2016211524","https://openalex.org/W2018705428","https://openalex.org/W2022781970","https://openalex.org/W2027457629","https://openalex.org/W2041580073","https://openalex.org/W2073787051","https://openalex.org/W2102531244","https://openalex.org/W2123405463","https://openalex.org/W2127498532","https://openalex.org/W2134491302","https://openalex.org/W2136074593","https://openalex.org/W2140135625","https://openalex.org/W2142971854","https://openalex.org/W2145049547","https://openalex.org/W2145487433","https://openalex.org/W2149365825","https://openalex.org/W2159178228","https://openalex.org/W2168947765","https://openalex.org/W2221321873","https://openalex.org/W2296360731","https://openalex.org/W2342548755","https://openalex.org/W2623785075","https://openalex.org/W2951057540","https://openalex.org/W3102923851","https://openalex.org/W4205513846","https://openalex.org/W4240038629","https://openalex.org/W6655145722","https://openalex.org/W6680657880","https://openalex.org/W6683042886","https://openalex.org/W6684877843","https://openalex.org/W6704800805","https://openalex.org/W6738947393","https://openalex.org/W6824062597","https://openalex.org/W6841545689"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Tasks":[0],"with":[1,40,129],"unknown":[2],"dynamics":[3,21],"and":[4,93,114,127],"costly":[5],"system":[6],"interaction":[7,26,133],"time":[8,27],"present":[9],"a":[10,17,50,58,122],"serious":[11],"challenge":[12],"for":[13,49],"reinforcement":[14],"learning.":[15],"If":[16],"model":[18,87],"of":[19,52,62,75,104,132],"the":[20,73,85,91,105],"can":[22,28,43],"be":[23,29],"learned":[24,86],"quickly,":[25],"reduced":[30],"substantially.":[31],"We":[32],"show":[33,98],"that":[34,88,99],"combining":[35],"an":[36,66],"optimistic":[37],"exploration":[38,67],"strategy":[39,68],"model-predictive":[41],"control":[42,121],"achieve":[44],"very":[45],"good":[46],"sample":[47],"complexity":[48],"range":[51],"nonlinear":[53],"systems.":[54],"Our":[55],"method":[56],"learns":[57],"Dirichlet":[59],"process":[60],"mixture":[61],"linear":[63],"models":[64],"using":[65],"based":[69],"on":[70,110],"optimism":[71],"in":[72,84],"face":[74],"uncertainty.":[76],"Trajectory":[77],"optimization":[78],"is":[79,115],"used":[80],"to":[81,117,120],"plan":[82],"paths":[83],"both":[89],"minimize":[90],"cost":[92],"perform":[94],"exploration.":[95],"Experimental":[96],"results":[97],"our":[100],"approach":[101],"achieves":[102],"some":[103],"most":[106],"sample-efficient":[107],"learning":[108],"rates":[109],"several":[111],"benchmark":[112],"problems,":[113],"able":[116],"successfully":[118],"learn":[119],"simulated":[123],"helicopter":[124],"during":[125],"hover":[126],"autorotation":[128],"only":[130],"seconds":[131],"time.":[134],"The":[135],"computational":[136],"requirements":[137],"are":[138],"substantial.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}