{"id":"https://openalex.org/W2801572960","doi":"https://doi.org/10.24963/ijcai.2018/451","title":"Fast Model Identification via Physics Engines for Data-Efficient Policy Search","display_name":"Fast Model Identification via Physics Engines for Data-Efficient Policy Search","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2801572960","doi":"https://doi.org/10.24963/ijcai.2018/451","mag":"2801572960"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/451","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/451","pdf_url":"https://www.ijcai.org/proceedings/2018/0451.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0451.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012487992","display_name":"Shaojun Zhu","orcid":"https://orcid.org/0000-0002-9653-5186"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojun Zhu","raw_affiliation_strings":["Department of Computer Science, Rutgers University, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041631345","display_name":"Andrew Kimmel","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Kimmel","raw_affiliation_strings":["Department of Computer Science, Rutgers University, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010667333","display_name":"Kostas E. Bekris","orcid":"https://orcid.org/0000-0002-0675-3324"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kostas E. Bekris","raw_affiliation_strings":["Department of Computer Science, Rutgers University, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068615270","display_name":"Abdeslam Boularias","orcid":"https://orcid.org/0000-0002-5587-4560"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdeslam Boularias","raw_affiliation_strings":["Department of Computer Science, Rutgers University, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0412,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93119921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3249","last_page":"3256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9854000210762024,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9850000143051147,"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/physics-engine","display_name":"Physics engine","score":0.705682635307312},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6564849615097046},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6186087727546692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.609384298324585},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.5476202368736267},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5097905993461609},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5026893615722656},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5000216960906982},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4831382930278778},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.45371824502944946},{"id":"https://openalex.org/keywords/dynamical-simulation","display_name":"Dynamical simulation","score":0.4499448835849762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43940645456314087},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43216896057128906},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4284176528453827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2024076282978058}],"concepts":[{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.705682635307312},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6564849615097046},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6186087727546692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609384298324585},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.5476202368736267},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5097905993461609},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5026893615722656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5000216960906982},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4831382930278778},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.45371824502944946},{"id":"https://openalex.org/C81587630","wikidata":"https://www.wikidata.org/wiki/Q5319044","display_name":"Dynamical simulation","level":2,"score":0.4499448835849762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43940645456314087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43216896057128906},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4284176528453827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2024076282978058},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/451","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/451","pdf_url":"https://www.ijcai.org/proceedings/2018/0451.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/451","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/451","pdf_url":"https://www.ijcai.org/proceedings/2018/0451.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2006546336","display_name":"NRI: INT: COLLAB: Integrated Modeling and Learning for Robust Grasping and Dexterous Manipulation with Adaptive Hands","funder_award_id":"1734492","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8489375509","display_name":"S&AS: FND: Reflective Learning of Stochastic Physical Models for Robust Manipulation","funder_award_id":"1723869","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2801572960.pdf","grobid_xml":"https://content.openalex.org/works/W2801572960.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1502922572","https://openalex.org/W1515851193","https://openalex.org/W1570792896","https://openalex.org/W1587009522","https://openalex.org/W1693986406","https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W1998179438","https://openalex.org/W2001685400","https://openalex.org/W2012392077","https://openalex.org/W2078856056","https://openalex.org/W2098030884","https://openalex.org/W2122458975","https://openalex.org/W2132602063","https://openalex.org/W2181623680","https://openalex.org/W2342662072","https://openalex.org/W2528489519","https://openalex.org/W2554830522","https://openalex.org/W2562736583","https://openalex.org/W2592857946","https://openalex.org/W2599719672","https://openalex.org/W2604883922","https://openalex.org/W2771827793","https://openalex.org/W2963149945","https://openalex.org/W2963614114","https://openalex.org/W2963892386","https://openalex.org/W2963930274","https://openalex.org/W2964112890","https://openalex.org/W2991459416","https://openalex.org/W3006111093","https://openalex.org/W4211049189","https://openalex.org/W4256333068","https://openalex.org/W4299906789","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2089992767","https://openalex.org/W2156767205","https://openalex.org/W3043483703","https://openalex.org/W622403409","https://openalex.org/W2969053614","https://openalex.org/W2567089594","https://openalex.org/W4387596100","https://openalex.org/W3127082165","https://openalex.org/W2940081677","https://openalex.org/W4383681401"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,33,54,60,83,107,122,126,138,143,163],"method":[4],"for":[5,45,81,124],"identifying":[6,125,151],"mechanical":[7,67],"parameters":[8,68],"of":[9,25,32,41,137,147,189],"robots":[10],"or":[11],"objects,":[12],"such":[13],"as":[14,70],"their":[15],"mass":[16],"and":[17,29,63,161,181],"friction":[18],"coefficients.":[19],"Key":[20],"features":[21],"are":[22],"the":[23,30,39,65,135,152,170,187],"use":[24],"off-the-shelf":[26],"physics":[27,55],"engines":[28],"adaptation":[31],"Bayesian":[34],"optimization":[35],"technique":[36],"towards":[37],"minimizing":[38],"number":[40],"real-world":[42,73,88],"experiments":[43,57],"needed":[44],"model-based":[46],"reinforcement":[47],"learning.":[48],"The":[49,75],"proposed":[50,171],"framework":[51],"reproduces":[52],"in":[53,85,104,159,174],"engine":[56],"performed":[58,157],"on":[59,150,162],"real":[61,102,164],"robot":[62],"optimizes":[64],"model's":[66],"so":[69],"to":[71,99,133],"match":[72],"trajectories.":[74],"optimized":[76],"model":[77,127,179],"is":[78,91,97,129],"then":[79],"used":[80],"learning":[82,182],"policy":[84,109,141,191],"simulation,":[86],"before":[87],"deployment.":[89],"It":[90],"well":[92],"understood,":[93],"however,":[94],"that":[95,128,169],"it":[96],"hard":[98],"exactly":[100],"reproduce":[101],"trajectories":[103],"simulation.":[105],"Moreover,":[106],"near-optimal":[108],"can":[110],"be":[111],"frequently":[112],"found":[113],"with":[114,142],"an":[115,175],"imperfect":[116],"model.":[117,155],"Therefore,":[118],"this":[119],"work":[120],"proposes":[121],"strategy":[123,172],"just":[130],"good":[131],"enough":[132],"approximate":[134],"value":[136],"locally":[139],"optimal":[140],"certain":[144],"confidence,":[145],"instead":[146],"wasting":[148],"effort":[149],"most":[153],"accurate":[154],"Evaluations,":[156],"both":[158],"simulation":[160],"robotic":[165],"manipulation":[166],"task,":[167],"indicate":[168],"results":[173],"overall":[176],"time-efficient,":[177],"integrated":[178],"identification":[180],"solution,":[183],"which":[184],"significantly":[185],"improves":[186],"data-efficiency":[188],"existing":[190],"search":[192],"algorithms.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}