{"id":"https://openalex.org/W3206393052","doi":"https://doi.org/10.1109/icra48506.2021.9561731","title":"SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning","display_name":"SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206393052","doi":"https://doi.org/10.1109/icra48506.2021.9561731","mag":"3206393052"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561731","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":"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/A5109476553","display_name":"Yifeng Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yifeng Jiang","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford, CA, USA","Robotics at Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Robotics at Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086928709","display_name":"Tingnan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingnan Zhang","raw_affiliation_strings":["Robotics at Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058408154","display_name":"Daniel E. Ho","orcid":"https://orcid.org/0000-0002-2195-5469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Ho","raw_affiliation_strings":["Everyday Robots, X The Moonshot Factory, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Everyday Robots, X The Moonshot Factory, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628285","display_name":"Yunfei Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunfei Bai","raw_affiliation_strings":["Everyday Robots, X The Moonshot Factory, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Everyday Robots, X The Moonshot Factory, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338914","display_name":"C. Karen Liu","orcid":"https://orcid.org/0000-0001-5926-0905"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Karen Liu","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"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/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"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":["EECS, University of California, Berkeley, Berkeley, CA, USA","Robotics at Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"EECS, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Robotics at Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103241086","display_name":"Jie Tan","orcid":"https://orcid.org/0000-0002-7947-0333"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Tan","raw_affiliation_strings":["Robotics at Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109476553"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":5.6323,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.96584666,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2884","last_page":"2890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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":0.9958000183105469,"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":0.9936000108718872,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8261398077011108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778825759887695},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.66464763879776},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6570509672164917},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.620415449142456},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6065523624420166},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5897945761680603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5495079159736633},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5208216905593872},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5182268619537354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5068967938423157},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49942708015441895},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.48978638648986816}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8261398077011108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778825759887695},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.66464763879776},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6570509672164917},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.620415449142456},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6065523624420166},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5897945761680603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5495079159736633},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5208216905593872},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5182268619537354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5068967938423157},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49942708015441895},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.48978638648986816},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561731","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W2087431993","https://openalex.org/W2099471712","https://openalex.org/W2105143952","https://openalex.org/W2159537373","https://openalex.org/W2529477964","https://openalex.org/W2534269850","https://openalex.org/W2562736583","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2605287558","https://openalex.org/W2736601468","https://openalex.org/W2758237641","https://openalex.org/W2801572960","https://openalex.org/W2890026535","https://openalex.org/W2911087563","https://openalex.org/W2919616510","https://openalex.org/W2938834661","https://openalex.org/W2952629144","https://openalex.org/W2952854274","https://openalex.org/W2962793481","https://openalex.org/W2962899390","https://openalex.org/W2962957005","https://openalex.org/W2962974944","https://openalex.org/W2963030226","https://openalex.org/W2963184939","https://openalex.org/W2963277051","https://openalex.org/W2963390419","https://openalex.org/W2963508354","https://openalex.org/W2963630234","https://openalex.org/W2968116426","https://openalex.org/W2980820015","https://openalex.org/W2981030070","https://openalex.org/W2990747716","https://openalex.org/W3003647188","https://openalex.org/W3008998212","https://openalex.org/W3010599703","https://openalex.org/W3010612407","https://openalex.org/W3029509103","https://openalex.org/W3035689006","https://openalex.org/W3035756007","https://openalex.org/W3037207827","https://openalex.org/W3037655992","https://openalex.org/W3039737909","https://openalex.org/W3097841467","https://openalex.org/W3101126850","https://openalex.org/W3101442004","https://openalex.org/W3129904619","https://openalex.org/W3130568950","https://openalex.org/W3131357870","https://openalex.org/W3132357684","https://openalex.org/W4287752583","https://openalex.org/W4288374418","https://openalex.org/W4297824641","https://openalex.org/W4320013936","https://openalex.org/W6675708744","https://openalex.org/W6718092244","https://openalex.org/W6728252718","https://openalex.org/W6728925229","https://openalex.org/W6731094094","https://openalex.org/W6735677848","https://openalex.org/W6736210646","https://openalex.org/W6741002519","https://openalex.org/W6744354654","https://openalex.org/W6745347688","https://openalex.org/W6754484421","https://openalex.org/W6754779071","https://openalex.org/W6756463683","https://openalex.org/W6761443123","https://openalex.org/W6765121789","https://openalex.org/W6768954891","https://openalex.org/W6775206470","https://openalex.org/W6779103169","https://openalex.org/W6779199252","https://openalex.org/W6780298656","https://openalex.org/W6780559895","https://openalex.org/W6781862982","https://openalex.org/W6784826119","https://openalex.org/W6912248530","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W4312352990","https://openalex.org/W4312246223"],"abstract_inverted_index":{"As":[0],"learning-based":[1],"approaches":[2],"progress":[3],"towards":[4],"automating":[5],"robot":[6],"controllers":[7],"design,":[8],"transferring":[9],"learned":[10,55],"policies":[11,111],"to":[12,31,41,46,58,77,109,119],"new":[13],"domains":[14],"with":[15,63],"different":[16],"dynamics":[17],"(e.g.":[18],"sim-to-real":[19],"transfer)":[20],"still":[21],"demands":[22],"manual":[23,64],"effort.":[24],"This":[25],"paper":[26],"introduces":[27],"SimGAN,":[28],"a":[29,37,54,87],"framework":[30],"tackle":[32],"domain":[33,141],"adaptation":[34],"by":[35],"identifying":[36],"hybrid":[38,68,97],"physics":[39,75],"simulator":[40,69,98],"match":[42],"the":[43,47,50,60,84,96,113,117],"simulated":[44],"trajectories":[45],"ones":[48],"from":[49],"target":[51,114],"domain,":[52,115],"using":[53],"discriminative":[56],"loss":[57,65],"address":[59],"limitations":[61],"associated":[62],"design.":[66],"Our":[67],"combines":[70],"neural":[71],"networks":[72],"and":[73,80,82,123],"traditional":[74],"simulation":[76],"balance":[78],"expressiveness":[79],"generalizability,":[81],"alleviates":[83],"need":[85,118],"for":[86,112,140],"carefully":[88],"selected":[89],"parameter":[90],"set":[91],"in":[92],"System":[93],"ID.":[94],"Once":[95],"is":[99],"identified":[100],"via":[101],"adversarial":[102],"reinforcement":[103],"learning,":[104],"it":[105],"can":[106],"be":[107],"used":[108],"refine":[110],"without":[116],"interleave":[120],"data":[121],"collection":[122],"policy":[124],"refinement.":[125],"We":[126],"show":[127],"that":[128],"our":[129],"approach":[130],"outperforms":[131],"multiple":[132],"strong":[133],"baselines":[134],"on":[135],"six":[136],"robotic":[137],"locomotion":[138],"tasks":[139],"adaptation.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}