{"id":"https://openalex.org/W2963781688","doi":"https://doi.org/10.1109/icra.2016.7487172","title":"Model-based reinforcement learning with parametrized physical models and optimism-driven exploration","display_name":"Model-based reinforcement learning with parametrized physical models and optimism-driven exploration","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2963781688","doi":"https://doi.org/10.1109/icra.2016.7487172","mag":"2963781688"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2016.7487172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081491793","display_name":"Chris Xie","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":"Chris Xie","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071959206","display_name":"Sachin Patil","orcid":"https://orcid.org/0000-0002-6247-2295"},"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":"Sachin Patil","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","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":false,"raw_author_name":"Teodor Moldovan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","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, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","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, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.6591,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96537469,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"504","last_page":"511"},"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9714999794960022,"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":0.8007345795631409},{"id":"https://openalex.org/keywords/optimism","display_name":"Optimism","score":0.6663833260536194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6584045886993408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4239605665206909},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3332296311855316},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15833455324172974},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05583810806274414}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8007345795631409},{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.6663833260536194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6584045886993408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4239605665206909},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3332296311855316},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15833455324172974},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05583810806274414}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2016.7487172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W53582479","https://openalex.org/W421662763","https://openalex.org/W1482341360","https://openalex.org/W1496720559","https://openalex.org/W1587009522","https://openalex.org/W1964946446","https://openalex.org/W1977655452","https://openalex.org/W1990005421","https://openalex.org/W1998179438","https://openalex.org/W2017756130","https://openalex.org/W2042520683","https://openalex.org/W2042795879","https://openalex.org/W2046633936","https://openalex.org/W2050883740","https://openalex.org/W2070513548","https://openalex.org/W2078856056","https://openalex.org/W2087617385","https://openalex.org/W2102154372","https://openalex.org/W2130440600","https://openalex.org/W2140135625","https://openalex.org/W2142971854","https://openalex.org/W2145049547","https://openalex.org/W2151186798","https://openalex.org/W2159178228","https://openalex.org/W2159537373","https://openalex.org/W2169209873","https://openalex.org/W2296360731","https://openalex.org/W4231367092","https://openalex.org/W4240038629","https://openalex.org/W4250730422","https://openalex.org/W6629680116","https://openalex.org/W6662048729","https://openalex.org/W6680657880","https://openalex.org/W6683042886","https://openalex.org/W6685331716","https://openalex.org/W6821826764"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2122713011","https://openalex.org/W2965399423","https://openalex.org/W4247284515","https://openalex.org/W2900331548","https://openalex.org/W2116758642","https://openalex.org/W2607406914","https://openalex.org/W2171209533","https://openalex.org/W3141834514","https://openalex.org/W2904519018"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,140],"present":[4,92],"a":[5,23,38,49,118,135,147],"robotic":[6,137],"model-based":[7],"reinforcement":[8],"learning":[9],"method":[10,113],"that":[11,29,111],"combines":[12],"ideas":[13],"from":[14,48],"model":[15,18,33,79],"identification":[16],"and":[17,43,60,87,105],"predictive":[19,67],"control.":[20],"We":[21,91],"use":[22],"feature-based":[24],"representation":[25],"of":[26,52,57,63,80,120,146,151],"the":[27,31,44,53,58,74,81,102,126],"dynamics":[28,32],"allows":[30],"to":[34,72,116],"be":[35],"fitted":[36],"with":[37],"simple":[39],"least":[40],"squares":[41],"procedure,":[42],"features":[45],"are":[46],"identified":[47],"high-level":[50],"specification":[51],"robot's":[54],"morphology,":[55],"consisting":[56],"number":[59],"connectivity":[61],"structure":[62],"its":[64],"links.":[65],"Model":[66],"control":[68,138,145],"is":[69,114],"then":[70],"used":[71],"choose":[73],"actions":[75],"under":[76],"an":[77,85],"optimistic":[78],"dynamics,":[82],"which":[83],"produces":[84],"efficient":[86],"goal-directed":[88],"exploration":[89],"strategy.":[90],"real":[93,143],"time":[94,144],"experimental":[95],"results":[96],"on":[97,134],"standard":[98],"benchmark":[99,121],"problems":[100],"involving":[101],"pendulum,":[103],"cartpole,":[104],"double":[106],"pendulum":[107],"systems.":[108],"Experiments":[109],"indicate":[110],"our":[112,132],"able":[115],"learn":[117],"range":[119],"tasks":[122],"substantially":[123],"faster":[124],"than":[125],"previous":[127],"best":[128],"methods.":[129],"To":[130],"evaluate":[131],"approach":[133],"realistic":[136],"task,":[139],"also":[141],"demonstrate":[142],"simulated":[148],"7":[149],"degree":[150],"freedom":[152],"arm.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}