{"id":"https://openalex.org/W2960705509","doi":"https://doi.org/10.1109/tpami.2019.2952353","title":"Assessing Transferability From Simulation to Reality for Reinforcement Learning","display_name":"Assessing Transferability From Simulation to Reality for Reinforcement Learning","publication_year":2019,"publication_date":"2019-11-08","ids":{"openalex":"https://openalex.org/W2960705509","doi":"https://doi.org/10.1109/tpami.2019.2952353","mag":"2960705509","pmid":"https://pubmed.ncbi.nlm.nih.gov/31722475"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2019.2952353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2952353","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.04685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056073467","display_name":"Fabio Muratore","orcid":"https://orcid.org/0000-0001-8600-2610"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210112253","display_name":"Honda (Germany)","ror":"https://ror.org/022c1xk47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210112253"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabio Muratore","raw_affiliation_strings":["Honda Research Institute Europe, Offenbach am Main, Germany","Intelligent Autonomous Systems Group, Technical University Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8600-2610","affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe, Offenbach am Main, Germany","institution_ids":["https://openalex.org/I4210112253"]},{"raw_affiliation_string":"Intelligent Autonomous Systems Group, Technical University Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025560073","display_name":"Michael Gienger","orcid":"https://orcid.org/0000-0001-8036-2519"},"institutions":[{"id":"https://openalex.org/I4210112253","display_name":"Honda (Germany)","ror":"https://ror.org/022c1xk47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210112253"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Gienger","raw_affiliation_strings":["Honda Research Institute Europe, Offenbach am Main, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8036-2519","affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe, Offenbach am Main, Germany","institution_ids":["https://openalex.org/I4210112253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems Group, Technical University Darmstadt, Darmstadt, Germany","Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, Technical University Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5297,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.9419883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"43","issue":"4","first_page":"1172","last_page":"1183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.987500011920929,"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":0.973800003528595,"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":0.6692706942558289},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6453030705451965},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.623688280582428},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.605185329914093},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5682801008224487},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5185033082962036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4996471405029297},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.48996320366859436},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.477870374917984},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.46218928694725037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4339217245578766},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4334179162979126},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3281311094760895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10421961545944214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692706942558289},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6453030705451965},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.623688280582428},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.605185329914093},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5682801008224487},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5185033082962036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4996471405029297},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.48996320366859436},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.477870374917984},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.46218928694725037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4339217245578766},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4334179162979126},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3281311094760895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10421961545944214},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2019.2952353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2952353","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:31722475","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31722475","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1907.04685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04685","pdf_url":"https://arxiv.org/pdf/1907.04685","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.04685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04685","pdf_url":"https://arxiv.org/pdf/1907.04685","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W598648183","https://openalex.org/W1481659984","https://openalex.org/W1507985183","https://openalex.org/W1522301498","https://openalex.org/W1746819321","https://openalex.org/W1832379062","https://openalex.org/W1966784014","https://openalex.org/W1969074599","https://openalex.org/W1978161072","https://openalex.org/W1990277704","https://openalex.org/W1995878217","https://openalex.org/W2000953623","https://openalex.org/W2001685400","https://openalex.org/W2076635261","https://openalex.org/W2117897510","https://openalex.org/W2145339207","https://openalex.org/W2205975260","https://openalex.org/W2534269850","https://openalex.org/W2586431331","https://openalex.org/W2595845486","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2621667117","https://openalex.org/W2623289472","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2767050701","https://openalex.org/W2773691349","https://openalex.org/W2785389871","https://openalex.org/W2885163910","https://openalex.org/W2898758998","https://openalex.org/W2952629144","https://openalex.org/W2962749646","https://openalex.org/W2962899390","https://openalex.org/W2962957005","https://openalex.org/W2963504951","https://openalex.org/W2963614114","https://openalex.org/W2963846183","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964121744","https://openalex.org/W2964198579","https://openalex.org/W2968116426","https://openalex.org/W2990747716","https://openalex.org/W3101442004","https://openalex.org/W4211049957","https://openalex.org/W4235001947","https://openalex.org/W4294238560","https://openalex.org/W4295549420","https://openalex.org/W4297686387","https://openalex.org/W4297918469","https://openalex.org/W4300799055","https://openalex.org/W6631190155","https://openalex.org/W6684921986","https://openalex.org/W6728925229","https://openalex.org/W6734129231","https://openalex.org/W6734827232","https://openalex.org/W6735677848","https://openalex.org/W6738747183","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6748519856","https://openalex.org/W6752818329","https://openalex.org/W6755890616"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"Learning":[0],"robot":[1],"control":[2,171],"policies":[3],"from":[4,41,174],"physics":[5,104],"simulations":[6,105],"is":[7,45,166],"of":[8,38,63,77,102,124,143],"great":[9],"interest":[10],"to":[11,43,60,127,140,168,183],"the":[12,19,28,35,61,64,72,78,82,88,100,103,125,138,141,160],"robotics":[13],"community":[14],"as":[15],"it":[16],"may":[17],"render":[18],"learning":[20],"process":[21],"faster,":[22],"cheaper,":[23],"and":[24],"safer":[25],"by":[26,94],"alleviating":[27],"need":[29],"for":[30,132],"expensive":[31],"real-world":[32],"experiments.":[33],"However,":[34],"direct":[36],"transfer":[37],"learned":[39],"behavior":[40,84],"simulation":[42],"reality":[44],"a":[46,50,53,129,170,175],"major":[47],"challenge.":[48],"Optimizing":[49],"policy":[51,163,172],"on":[52,151],"slightly":[54],"faulty":[55],"simulator":[56,79],"can":[57,85,179],"easily":[58],"lead":[59],"maximization":[62],"'Simulation":[65],"Optimization":[66,115],"Bias'":[67],"(SOB).":[68],"In":[69],"this":[70,92],"case,":[71],"optimizer":[73],"exploits":[74],"modeling":[75],"errors":[76],"such":[80],"that":[81,159],"resulting":[83],"potentially":[86],"damage":[87],"robot.":[89],"We":[90,108],"tackle":[91],"challenge":[93],"applying":[95],"domain":[96],"randomization,":[97],"i.e.,":[98],"randomizing":[99],"parameters":[101],"during":[106],"learning.":[107],"propose":[109],"an":[110,122],"algorithm":[111,165],"called":[112],"Simulation-based":[113],"Policy":[114],"with":[116],"Transferability":[117],"Assessment":[118],"(SPOTA)":[119],"which":[120,178],"uses":[121],"estimator":[123,136],"SOB":[126],"formulate":[128],"stopping":[130],"criterion":[131],"training.":[133,147,189],"The":[134],"introduced":[135],"quantifies":[137],"over-fitting":[139],"set":[142],"domains":[144],"experienced":[145],"while":[146],"Our":[148],"experimental":[149],"results":[150],"two":[152],"different":[153],"second":[154],"order":[155],"nonlinear":[156],"systems":[157,185],"show":[158],"new":[161],"simulation-based":[162],"search":[164],"able":[167],"learn":[169],"exclusively":[173],"randomized":[176],"simulator,":[177],"be":[180],"applied":[181],"directly":[182],"real":[184],"without":[186],"any":[187],"additional":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}