Robot Learning From Randomized Simulations: A Review
The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data gener...
Uloženo v:
| Vydáno v: | Frontiers in robotics and AI Ročník 9; s. 799893 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Switzerland
Frontiers Media S.A
11.04.2022
|
| Témata: | |
| ISSN: | 2296-9144, 2296-9144 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the “reality gap.” We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named “domain randomization” which is a method for learning from randomized simulations. |
|---|---|
| AbstractList | The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the “reality gap.” We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named “domain randomization” which is a method for learning from randomized simulations. The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the "reality gap." We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named "domain randomization" which is a method for learning from randomized simulations.The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the "reality gap." We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named "domain randomization" which is a method for learning from randomized simulations. |
| Author | Gienger, Michael Turk, Greg Ramos, Fabio Yu, Wenhao Peters, Jan Muratore, Fabio |
| AuthorAffiliation | 6 Robotics at Google , Mountain View , CA , United States 1 Intelligent Autonomous Systems Group , Technical University of Darmstadt , Darmstadt , Germany 3 School of Computer Science , University of Sydney , Sydney , NSW , Australia 4 NVIDIA , Seattle , WA , United States 5 Georgia Institute of Technology , Atlanta , GA , United States 2 Honda Research Institute Europe , Offenbach am Main , Germany |
| AuthorAffiliation_xml | – name: 6 Robotics at Google , Mountain View , CA , United States – name: 2 Honda Research Institute Europe , Offenbach am Main , Germany – name: 3 School of Computer Science , University of Sydney , Sydney , NSW , Australia – name: 4 NVIDIA , Seattle , WA , United States – name: 5 Georgia Institute of Technology , Atlanta , GA , United States – name: 1 Intelligent Autonomous Systems Group , Technical University of Darmstadt , Darmstadt , Germany |
| Author_xml | – sequence: 1 givenname: Fabio surname: Muratore fullname: Muratore, Fabio – sequence: 2 givenname: Fabio surname: Ramos fullname: Ramos, Fabio – sequence: 3 givenname: Greg surname: Turk fullname: Turk, Greg – sequence: 4 givenname: Wenhao surname: Yu fullname: Yu, Wenhao – sequence: 5 givenname: Michael surname: Gienger fullname: Gienger, Michael – sequence: 6 givenname: Jan surname: Peters fullname: Peters, Jan |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35494543$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kUtv1DAUhS1URB_0B7BBWbKZ4fqRxGaBVFW0VBoJaYC15evcDK4Su9iZVvDrSWdK1bJgZcv3nO8e-Ryzg5giMfaGw1JKbd73OeG0FCDEsjVGG_mCHQlhmoXhSh08uR-y01KuAYDXWsm2fcUOZa2MqpU8YmqdME3VilyOIW6qi5zGau1il8bwm7rqaxi3g5tCiuVDdVat6TbQ3Wv2sndDodOH84R9v_j07fzzYvXl8ur8bLXwteTTQiF48MqAk85jB-BQKFQSQfe9FjhnAMGp19jxhohLISVqj9K12PhWyBN2ted2yV3bmxxGl3_Z5ILdPaS8sS5PwQ9kueCARnWN9EqhqxE7ap3mnhzMAfqZ9XHPutniSJ2nOGU3PIM-n8Tww27SrTUgtVZqBrx7AOT0c0tlsmMonobBRUrbYkVT66YWoGCWvn2663HJ32-fBXwv8DmVkql_lHCw9-3aXbv2vl27b3f2tP94fJh2zcxxw_Af5x_Nvarv |
| CitedBy_id | crossref_primary_10_3390_s25113394 crossref_primary_10_1109_LRA_2024_3398428 crossref_primary_10_1109_LRA_2025_3559833 crossref_primary_10_1109_OJVT_2025_3573647 crossref_primary_10_1016_j_iintel_2024_100098 crossref_primary_10_1109_TICPS_2025_3589351 crossref_primary_10_1109_ACCESS_2023_3278208 crossref_primary_10_1016_j_sysconle_2024_106011 crossref_primary_10_1007_s11042_024_19731_6 crossref_primary_10_1109_TRO_2025_3539192 crossref_primary_10_1007_s11044_024_10005_5 crossref_primary_10_1109_ACCESS_2023_3324039 crossref_primary_10_1109_MRA_2022_3207664 crossref_primary_10_1109_JAS_2023_123375 crossref_primary_10_1177_02783649251318046 crossref_primary_10_3390_electronics11111754 crossref_primary_10_3390_mti8030018 crossref_primary_10_1177_02783649231184498 crossref_primary_10_1177_02783649241273565 crossref_primary_10_1016_j_procs_2022_11_058 crossref_primary_10_1109_TASE_2024_3432405 crossref_primary_10_3390_jmse13091627 crossref_primary_10_1109_LRA_2024_3521178 crossref_primary_10_1109_ACCESS_2024_3390035 crossref_primary_10_3390_robotics11050109 crossref_primary_10_1016_j_neucom_2024_128951 crossref_primary_10_3389_fbioe_2024_1334643 crossref_primary_10_1109_ACCESS_2023_3249572 crossref_primary_10_1126_scirobotics_adi8022 crossref_primary_10_3390_technologies13050198 |
| Cites_doi | 10.3390/robotics9010008 10.15607/RSS.2006.II.032 10.1145/1833351.177881010.1145/1778765.1778810 10.1093/biomet/asp052 10.1109/TRO.2019.2958211 10.1145/566654.566636 10.15607/RSS.2018.XIV.008 10.1109/ICRA48506.2021.9562091 10.15607/RSS.2012.VIII.045 10.1007/s11263-015-0816-y 10.1177/0278364913495721 10.1080/01621459.1949.10483310 10.1609/aaai.v24i1.7727 10.1126/science.1133687 10.1098/rspa.2007.1900 10.1109/IROS.2017.8206245 10.1007/978-1-84628-517-2 10.1007/978-0-85729-664-1 10.1073/pnas.1912789117 10.1371/journal.pcbi.1002803 10.1109/JPROC.2020.3004555 10.1109/TAC.2015.2444134 10.15607/RSS.2021.XVII.011 10.1109/ICRA48506.2021.9561805 10.15607/RSS.2021.XVII.061 10.1109/ICRA48506.2021.9561731 10.1038/nature16961 10.1016/S0004-3702(99)00052-1 10.1007/BF00992696 10.1111/j.1468-5914.1975.tb00350.x 10.15607/RSS.2019.XV.029 10.1007/s10107-006-0720-x 10.1109/LRA.2020.3013848 10.1109/TPAMI.2019.2952353 10.1109/TKDE.2009.191 10.1023/A:101823700882310.1007/bf00117447 10.1109/LRA.2019.2920285 10.1177/0278364919887447 10.1109/ICRA.2017.7989186 10.15607/RSS.2021.XVII.068 10.1177/105971239700600205 10.1016/S0167-6377(98)00054-6 10.1016/j.neunet.2010.08.011 10.1111/j.1467-9868.2011.01010.x 10.1109/TCSI.2012.2215396 10.1109/ICRA48506.2021.9560935 10.1177/027836498600500306 10.15607/RSS.2020.XVI.064 10.15607/RSS.2017.XIII.048 10.1287/opre.1.5.263 10.1007/s11263-009-0233-1 10.1073/pnas.0306899100 10.1038/nature14422 10.1287/opre.1090.0741 10.15607/RSS.2018.XIV.010 10.1002/rob.21683 10.1007/bf00337259 10.3389/fnbot.2019.00006 10.1145/122344.122377 10.1007/bf00275151 10.1177/0278364917710318 10.1109/TEVC.2012.2185849 10.1287/mnsc.25.7.649 10.15607/RSS.2017.XIII.034 10.15607/RSS.2021.XVII.063 10.1007/bf00535296 10.1073/pnas.1306572110 10.15607/RSS.2021.XVII.007 10.1002/cav.1712 10.1561/2300000021 10.1038/nature14236 10.1109/LRA.2021.3052391 |
| ContentType | Journal Article |
| Copyright | Copyright © 2022 Muratore, Ramos, Turk, Yu, Gienger and Peters. Copyright © 2022 Muratore, Ramos, Turk, Yu, Gienger and Peters. 2022 Muratore, Ramos, Turk, Yu, Gienger and Peters |
| Copyright_xml | – notice: Copyright © 2022 Muratore, Ramos, Turk, Yu, Gienger and Peters. – notice: Copyright © 2022 Muratore, Ramos, Turk, Yu, Gienger and Peters. 2022 Muratore, Ramos, Turk, Yu, Gienger and Peters |
| DBID | AAYXX CITATION NPM 7X8 5PM DOA |
| DOI | 10.3389/frobt.2022.799893 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | CrossRef PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitleAlternate | Muratore et al |
| EISSN | 2296-9144 |
| ExternalDocumentID | oai_doaj_org_article_1210b94d63c44ba5bbde7a81cea090af PMC9038844 35494543 10_3389_frobt_2022_799893 |
| Genre | Journal Article Review |
| GroupedDBID | 53G 5VS 9T4 AAFWJ AAYXX ACGFS ADBBV AFPKN ALMA_UNASSIGNED_HOLDINGS BCNDV CITATION GROUPED_DOAJ KQ8 M~E OK1 PGMZT RPM ACXDI IAO ICD IEA IPNFZ ISR NPM RIG 7X8 5PM |
| ID | FETCH-LOGICAL-c531t-4b0c0c490a3acbd00ab24b43b08ff82b494021ef8bd16ee13233b8cb3a7b6c723 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 51 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000792457300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2296-9144 |
| IngestDate | Fri Oct 03 12:53:31 EDT 2025 Thu Aug 21 18:17:42 EDT 2025 Fri Sep 05 10:04:37 EDT 2025 Thu Jan 02 22:27:44 EST 2025 Sat Nov 29 05:50:08 EST 2025 Tue Nov 18 22:20:27 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | simulation optimization bias reality gap simulation robotics sim-to-real domain randomization reinforcement learning |
| Language | English |
| License | Copyright © 2022 Muratore, Ramos, Turk, Yu, Gienger and Peters. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c531t-4b0c0c490a3acbd00ab24b43b08ff82b494021ef8bd16ee13233b8cb3a7b6c723 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 ObjectType-Review-3 content type line 23 Konstantinos Chatzilygeroudis, University of Patras, Greece Reviewed by: Akansel Cosgun, Monash University, Australia This article was submitted to Robot Learning and Evolution, a section of the journal Frontiers in Robotics and AI Edited by: Antonio Fernández-Caballero, University of Castilla-La Mancha, Spain |
| OpenAccessLink | https://doaj.org/article/1210b94d63c44ba5bbde7a81cea090af |
| PMID | 35494543 |
| PQID | 2658652040 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_1210b94d63c44ba5bbde7a81cea090af pubmedcentral_primary_oai_pubmedcentral_nih_gov_9038844 proquest_miscellaneous_2658652040 pubmed_primary_35494543 crossref_primary_10_3389_frobt_2022_799893 crossref_citationtrail_10_3389_frobt_2022_799893 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-04-11 |
| PublicationDateYYYYMMDD | 2022-04-11 |
| PublicationDate_xml | – month: 04 year: 2022 text: 2022-04-11 day: 11 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland |
| PublicationTitle | Frontiers in robotics and AI |
| PublicationTitleAlternate | Front Robot AI |
| PublicationYear | 2022 |
| Publisher | Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media S.A |
| References | Van Parys (B170) 2015; 61 Metropolis (B118) 1949; 44 Zhang (B185) 2021 Craik (B39) 1943 Huang (B73) 2017 Peng (B136) 2018 Teh (B165) 2017 Jakobi (B76) 1997; 6 Kakade (B84) 2001 Wittenmark (B175) 1995 Cully (B42) 2015; 521 Chatzilygeroudis (B29) 2017 James (B79) 2019 Kaspar (B85) 2020 Allevato (B3) 2019 Martin Martin (B113) 2014 Alghonaim (B2) 2020 Andrychowicz (B5) 2017 Degrave (B48) 2019; 13 Goodfellow (B62) 2015 Lutter (B107) 2019 Szegedy (B163) 2014 Jiang (B80) 2021 Pinto (B139) 2018 Ramos (B146) 2019 Bengio (B18) 2009 Barcelos (B12) 2021 Xie (B179) 2020 Carlini (B27) 2017 B38 Klink (B88) 2019 Yu (B184) 2017 Levine (B100) 2018; 37 Russakovsky (B150) 2015; 115 Zhou (B188) 1998 Dai (B47) 2019 Bayraksan (B16) 2006; 108 Williams (B174) 1992; 8 Lutter (B106) Peters (B138) 2010 Watson (B173) 2021 Krizhevsky (B93) 2012 Christiano (B34) 2016 Zhen (B187) 2021 Chow (B33) 1963; 2 Ting (B167) 2006 Bousmalis (B21) 2018 Muratore (B125); 43 Siekmann (B157) 2021 Yang (B181) 2013; 60 Battaglia (B15) 2016 Kahn (B83) 1953; 1 Mandlekar (B110) 2017 Polvara (B141) 2020; 9 Levine (B99) 2013 Brockman (B22) 2016 Mehta (B117) 2020 James (B78) 2017 Krotkov (B94) 2017; 34 Matl (B115) 2020 Yu (B183) Atkeson (B10) 1986; 5 Chebotar (B31) 2019 Kumar (B95) 2021 Rajeswaran (B145) 2020 Paul (B135) 2019 Heiden (B69) 2021 Deisenroth (B50) 2011 Muratore (B126) Parisotto (B134) 2016 Wang (B171) 2017 Baker (B11) 2020 Liu (B102) 2017 Czarnecki (B45) 2019 Matas (B114) 2018 Feldbaum (B59) 1960; 21 Amari (B4) 1977; 27 Durkan (B54) 2020 Dennett (B52) 1975 Sunnåker (B159) 2013; 9 Sutton (B161) 1991; 2 Tobin (B168) 2017 Marco (B111) 2017 Brosseit (B25) 2021 Santoro (B155) 2016 Yu (B182) Wu (B177) 2015 Bongard (B20) 2006; 314 Lutter (B108) Papamakarios (B132) 2016 Rasmussen (B147) 2006 Hanna (B68) 2017 Ruiz (B149) 2019 Ciresan (B36) 2012 Greydanus (B65) 2019 Silver (B158) 2016; 529 Barcelos (B13) 2020 Lillicrap (B101) 2016 Pan (B131) 2010; 22 Forrester (B61) 2007; 463 Kadian (B82) 2020; 5 Tan (B164) 2018 Jakobi (B77) 1995 Molchanov (B120) 2019 Papamakarios (B133) 2019 Brogliato (B23) 2007; 2 Ilyas (B74) 2019 Koos (B91) 2010 Marjoram (B112) 2003; 100 Du (B53) 2021 Kumar (B96) 2010 Battaglia (B14) 2013; 110 Mordatch (B121) 2015 Cranmer (B40) 2020; 117 Rusu (B153) 2017 Åström (B9) 2008 Koos (B92) 2013; 17 Lowrey (B103) 2018 Abdulsamad (B1) 2021 Kurakin (B97) 2017 Rawlik (B148) 2012 Ting (B166) 2011; 24 Chatzilygeroudis (B28) 2018 Collins (B37) 2019 Kishimoto (B86) 1979; 7 Erez (B55) 2008 Klink (B87) 2021 Muratore (B124); 6 Zhuang (B189) 2021; 109 Mnih (B119) 2015; 518 Mozian (B123) 2020 Zhang (B186) 2020 Sutanto (B160) 2020 Körber (B81) 2021 Antonova (B7) 2019 Wang (B172) 2010; 29 Kolev (B90) 2009; 84 Andrychowicz (B6) 2020; 39 Beaumont (B17) 2009; 96 Deisenroth (B49) 2011; 2 Fearnhead (B58) 2012; 74 Asada (B8) 1996; 23 Ng (B129) 2000 Chen (B32) 2017 Possas (B142) 2020 Haefner (B67) 2018 Morere (B122) 2019; 4 OpenAI (B130) 2019 Rusu (B152) Fawzi (B57) 2015 Luksch (B105) 2012 Ivaldi (B75) 2014 Muratore (B127) 2018 Wright (B176) 1979; 25 Xie (B178) 2019 Kober (B89) 2013; 32 Cutler (B43) 2016 Grant (B63) 2018 Landau (B98) 2011 Mehta (B116) 2019 Nagabandi (B128) 2019 Höfer (B66) 2020 Bin Peng (B19) 2020 Chung (B35) 2016; 27 Dai (B46) 2021 Perlin (B137) 2002; 21 Sadeghi (B154) 2017 Yan (B180) 2020 Rajeswaran (B144) 2017 Chatzilygeroudis (B30) 2020; 36 van den Oord (B169) 2018 Erez (B56) 2015 Finn (B60) 2017 Cui (B41) 2017 Greenberg (B64) 2019 Mak (B109) 1999; 24 Rusu (B151) Cutler (B44) 2015 Pinto (B140) 2017 Hu (B72) 2019 Radford (B143) 2019 Calandra (B26) 2015 Lueckmann (B104) 2017 Sutton (B162) 1999; 112 Hinton (B71) 2015 Schulman (B156) 2017 Hermans (B70) 2020 Delage (B51) 2010; 58 Brooks (B24) 1992 |
| References_xml | – start-page: 1531 year: 2001 ident: B84 article-title: A Natural Policy Gradient – year: 2018 ident: B169 article-title: Representation Learning with Contrastive Predictive Coding – start-page: 564 year: 2020 ident: B180 article-title: Learning Predictive Representations for Deformable Objects Using Contrastive Estimation – start-page: 04616 year: 2021 ident: B81 article-title: Comparing Popular Simulation Environments in the Scope of Robotics and Reinforcement Learning – ident: B152 article-title: Progressive Neural Networks – volume-title: Language Models Are Unsupervised Multitask Learners year: 2019 ident: B143 – start-page: 125 year: 2019 ident: B74 article-title: Adversarial Examples Are Not Bugs, They Are Features – volume: 9 start-page: 8 year: 2020 ident: B141 article-title: Sim-to-real Quadrotor landing via Sequential Deep Q-Networks and Domain Randomization publication-title: Robotics doi: 10.3390/robotics9010008 – start-page: 6706 year: 2019 ident: B37 article-title: Quantifying the Reality gap in Robotic Manipulation Tasks – year: 2006 ident: B167 article-title: A Bayesian Approach to Nonlinear Parameter Identification for Rigid Body Dynamics doi: 10.15607/RSS.2006.II.032 – start-page: 2771 year: 2020 ident: B54 article-title: On Contrastive Learning for Likelihood-free Inference – year: 2020 ident: B179 article-title: Dynamics Randomization Revisited: A Case Study for Quadrupedal Locomotion – start-page: 334 year: 2017 ident: B78 article-title: Transferring End-To-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task – volume: 29 start-page: 73 year: 2010 ident: B172 article-title: Optimizing Walking Controllers for Uncertain Inputs and Environments publication-title: ACM Trans. Graphics doi: 10.1145/1833351.177881010.1145/1778765.1778810 – start-page: 3642 year: 2012 ident: B36 article-title: Multi-column Deep Neural Networks for Image Classification – volume-title: Essentials of Robust Control year: 1998 ident: B188 – start-page: 5048 year: 2017 ident: B5 article-title: Hindsight Experience Replay – year: 2016 ident: B34 article-title: Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model – year: 2020 ident: B11 article-title: Emergent Tool Use from Multi-Agent Autocurricula – volume: 96 start-page: 983 year: 2009 ident: B17 article-title: Adaptive Approximate Bayesian Computation publication-title: Biometrika doi: 10.1093/biomet/asp052 – start-page: 207 year: 2013 ident: B99 article-title: Variational Policy Search via Trajectory Optimization – start-page: 4239 year: 2020 ident: B70 article-title: Likelihood-free MCMC with Amortized Approximate Ratio Estimators – start-page: 59 year: 2019 ident: B120 article-title: Sim-to-(multi)-real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors – start-page: 13176 volume-title: A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning year: 2021 ident: B87 – start-page: 4502 year: 2016 ident: B15 article-title: Interaction Networks for Learning about Objects, Relations and Physics – volume: 36 start-page: 328 year: 2020 ident: B30 article-title: A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials publication-title: IEEE Trans. Robot. doi: 10.1109/TRO.2019.2958211 – volume: 21 start-page: 681 year: 2002 ident: B137 article-title: Improving Noise publication-title: ACM Trans. Graph. doi: 10.1145/566654.566636 – year: 2020 ident: B117 article-title: A User‘s Guide to Calibrating Robotics Simulators – year: 2016 ident: B134 article-title: Actor-mimic: Deep Multitask and Transfer Reinforcement Learning – ident: B183 article-title: Policy Transfer with Strategy Optimization – ident: B151 article-title: Policy Distillation – year: 2018 ident: B139 article-title: Asymmetric Actor Critic for Image-Based Robot Learning doi: 10.15607/RSS.2018.XIV.008 – start-page: 164 year: 2018 ident: B67 article-title: Fight Ill-Posedness with Ill-Posedness: Single-Shot Variational Depth Super-resolution from Shading – year: 2016 ident: B101 article-title: Continuous Control with Deep Reinforcement Learning – start-page: 1289 year: 2017 ident: B104 article-title: Flexible Statistical Inference for Mechanistic Models of Neural Dynamics – volume-title: Adaptive Control year: 2008 ident: B9 – year: 2019 ident: B107 article-title: Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning – start-page: 700 year: 2018 ident: B127 article-title: Domain Randomization for Simulation-Based Policy Optimization with Transferability Assessment – ident: B38 – volume-title: Auto-tuned Sim-To-Real Transfer year: 2021 ident: B53 doi: 10.1109/ICRA48506.2021.9562091 – year: 2015 ident: B62 article-title: Explaining and Harnessing Adversarial Examples – year: 2012 ident: B148 article-title: On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference doi: 10.15607/RSS.2012.VIII.045 – start-page: 10969 year: 2020 ident: B13 article-title: DISCO: Double Likelihood-free Inference Stochastic Control – start-page: 1331 year: 2019 ident: B45 article-title: Distilling Policy Distillation – volume: 115 start-page: 211 year: 2015 ident: B150 article-title: Imagenet Large Scale Visual Recognition challenge publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-015-0816-y – start-page: 4496 year: 2017 ident: B165 article-title: Distral: Robust Multitask Reinforcement Learning – start-page: 445 volume-title: Proc. Machine Learn. Res. year: 2019 ident: B3 article-title: Tunenet: One-Shot Residual Tuning for System Identification and Sim-To-Real Robot Task Transfer – year: 2019 ident: B130 article-title: Solving Rubik’s Cube with a Robot Hand – year: 2021 ident: B185 article-title: Robust Reinforcement Learning on State Observations with Learned Optimal Adversary – start-page: 41 year: 2009 ident: B18 article-title: Curriculum Learning – start-page: 1106 volume-title: Lake Tahoe, Nev. United States December year: 2012 ident: B93 article-title: Imagenet Classification with Deep Convolutional Neural Networks – start-page: 1189 year: 2010 ident: B96 article-title: Self-paced Learning for Latent Variable Models – volume: 32 start-page: 1238 year: 2013 ident: B89 article-title: Reinforcement Learning in Robotics: A Survey publication-title: Int. J. Robotics Res. doi: 10.1177/0278364913495721 – volume: 44 start-page: 335 year: 1949 ident: B118 article-title: The Monte Carlo Method publication-title: J. Am. Stat. Assoc. doi: 10.1080/01621459.1949.10483310 – year: 2010 ident: B138 article-title: Relative Entropy Policy Search doi: 10.1609/aaai.v24i1.7727 – volume: 314 start-page: 1118 year: 2006 ident: B20 article-title: Resilient Machines through Continuous Self-Modeling publication-title: Science doi: 10.1126/science.1133687 – volume: 463 start-page: 3251 year: 2007 ident: B61 article-title: Multi-fidelity Optimization via Surrogate Modelling publication-title: Proc. R. Soc. A. doi: 10.1098/rspa.2007.1900 – year: 2017 ident: B110 article-title: Adversarially Robust Policy Learning: Active Construction of Physically-Plausible Perturbations doi: 10.1109/IROS.2017.8206245 – year: 2021 ident: B187 article-title: Mathematical Foundations of Robust and Distributionally Robust Optimization – start-page: 127 year: 2015 ident: B177 article-title: Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning – start-page: 5445 year: 2020 ident: B142 article-title: Online Bayessim for Combined Simulator Parameter Inference and Policy Improvement – volume: 2 year: 2007 ident: B23 article-title: Dissipative Systems Analysis and Control publication-title: Theor. Appl. doi: 10.1007/978-1-84628-517-2 – start-page: 215 year: 2008 ident: B55 article-title: What Does Shaping Mean for Computational Reinforcement Learning? – volume-title: Adaptive Control: Algorithms, Analysis and Applications year: 2011 ident: B98 doi: 10.1007/978-0-85729-664-1 – start-page: 03149 volume-title: Destilled Domain Randomization year: 2021 ident: B25 – volume: 117 start-page: 30055 year: 2020 ident: B40 article-title: The Frontier of Simulation-Based Inference publication-title: Proc. Natl. Acad. Sci. USA doi: 10.1073/pnas.1912789117 – start-page: 2404 year: 2019 ident: B64 article-title: Automatic Posterior Transformation for Likelihood-free Inference – volume: 9 start-page: e1002803 year: 2013 ident: B159 article-title: Approximate Bayesian Computation publication-title: Plos Comput. Biol. doi: 10.1371/journal.pcbi.1002803 – volume: 109 start-page: 43 year: 2021 ident: B189 article-title: A Comprehensive Survey on Transfer Learning publication-title: Proc. IEEE doi: 10.1109/JPROC.2020.3004555 – volume: 61 start-page: 1 year: 2015 ident: B170 article-title: Distributionally Robust Control of Constrained Stochastic Systems publication-title: IEEE Trans. Automat. Contr. doi: 10.1109/TAC.2015.2444134 – year: 2021 ident: B95 article-title: RMA: Rapid Motor Adaptation for Legged Robots doi: 10.15607/RSS.2021.XVII.011 – year: 2015 ident: B57 article-title: Fundamental Limits on Adversarial Robustness – start-page: 2770 year: 2020 ident: B115 article-title: Inferring the Material Properties of Granular media for Robotic Tasks – start-page: 5442 year: 2016 ident: B43 article-title: Autonomous Drifting Using Simulation-Aided Reinforcement Learning – start-page: 456 year: 2019 ident: B7 article-title: Bayesian Optimization in Variational Latent Spaces with Dynamic Compression – ident: B108 article-title: Differentiable Physics Models for Real-World Offline Model-Based Reinforcement Learning doi: 10.1109/ICRA48506.2021.9561805 – start-page: 734 year: 2018 ident: B114 article-title: Sim-to-real Reinforcement Learning for Deformable Object Manipulation – year: 2021 ident: B157 article-title: Blind Bipedal Stair Traversal via Sim-To-Real Reinforcement Learning doi: 10.15607/RSS.2021.XVII.061 – start-page: 7953 year: 2020 ident: B145 article-title: A Game Theoretic Framework for Model Based Reinforcement Learning – year: 2021 ident: B80 article-title: Simgan: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning doi: 10.1109/ICRA48506.2021.9561731 – start-page: 2494 year: 2014 ident: B113 article-title: Online Interactive Perception of Articulated Objects with Multi-Level Recursive Estimation Based on Task-specific Priors – volume: 529 start-page: 484 year: 2016 ident: B158 article-title: Mastering the Game of Go with Deep Neural Networks and Tree Search publication-title: Nature doi: 10.1038/nature16961 – volume: 112 start-page: 181 year: 1999 ident: B162 article-title: Between Mdps and Semi-mdps: A Framework for Temporal Abstraction in Reinforcement Learning publication-title: Artif. Intelligence doi: 10.1016/S0004-3702(99)00052-1 – volume: 8 start-page: 229 year: 1992 ident: B174 article-title: Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning publication-title: Mach Learn. doi: 10.1007/BF00992696 – year: 1975 ident: B52 article-title: Why the Law of Effect Will Not Go Away publication-title: J. Theor. Soc. Behav. doi: 10.1111/j.1468-5914.1975.tb00350.x – year: 2019 ident: B146 article-title: Bayessim: Adaptive Domain Randomization via Probabilistic Inference for Robotics Simulators doi: 10.15607/RSS.2019.XV.029 – volume: 108 start-page: 495 year: 2006 ident: B16 article-title: Assessing Solution Quality in Stochastic Programs publication-title: Math. Program doi: 10.1007/s10107-006-0720-x – start-page: 1 year: 2018 ident: B28 article-title: Using Parameterized Black-Box Priors to Scale up Model-Based Policy Search for Robotics – start-page: 1 year: 2018 ident: B136 article-title: Sim-to-real Transfer of Robotic Control with Dynamics Randomization – start-page: 1028 year: 2016 ident: B132 article-title: Fast ϵ-free Inference of Simulation Models with Bayesian Conditional Density Estimation – volume: 5 start-page: 6670 year: 2020 ident: B82 article-title: Sim2real Predictivity: Does Evaluation in Simulation Predict Real-World Performance? publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2020.3013848 – volume: 43 start-page: 1172 ident: B125 article-title: Assessing Transferability from Simulation to Reality for Reinforcement Learning publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2019.2952353 – volume: 22 start-page: 1345 year: 2010 ident: B131 article-title: A Survey on Transfer Learning publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2009.191 – start-page: 23 year: 2017 ident: B168 article-title: Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World – volume: 23 start-page: 279 year: 1996 ident: B8 article-title: Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning publication-title: Mach. Learn. doi: 10.1023/A:101823700882310.1007/bf00117447 – start-page: 4825 year: 2017 ident: B41 article-title: Knowledge Distillation across Ensembles of Multilingual Models for Low-Resource Languages – volume: 4 start-page: 2815 year: 2019 ident: B122 article-title: Learning to Plan Hierarchically from Curriculum publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2019.2920285 – year: 2017 ident: B144 article-title: Epopt: Learning Robust Neural Network Policies Using Model Ensembles – year: 2017 ident: B97 article-title: Adversarial Examples in the Physical World – start-page: 317 year: 2019 ident: B178 article-title: Learning Locomotion Skills for Cassie: Iterative Design and Sim-To-Real – volume: 39 start-page: 3 year: 2020 ident: B6 article-title: Learning Dexterous In-Hand Manipulation publication-title: Int. J. Robotics Res. doi: 10.1177/0278364919887447 – start-page: 2605 year: 2015 ident: B44 article-title: Efficient Reinforcement Learning for Robots Using Informative Simulated Priors – start-page: 3186 year: 2015 ident: B26 article-title: Learning Inverse Dynamics Models with Contacts – volume-title: Proximal Policy Optimization Algorithms year: 2017 ident: B156 – year: 2017 ident: B111 article-title: Virtual vs. Real: Trading off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization doi: 10.1109/ICRA.2017.7989186 – start-page: 3 year: 1992 ident: B24 article-title: Artificial Life and Real Robots – start-page: 15353 year: 2019 ident: B65 article-title: Hamiltonian Neural Networks – year: 2021 ident: B12 article-title: Dual Online Stein Variational Inference for Control and Dynamics doi: 10.15607/RSS.2021.XVII.068 – start-page: 6265 year: 2019 ident: B72 article-title: Chainqueen: A Real-Time Differentiable Physical Simulator for Soft Robotics – volume-title: Gaussian Processes for Machine Learning year: 2006 ident: B147 – year: 2018 ident: B63 article-title: Recasting Gradient-Based Meta-Learning as Hierarchical Bayes – start-page: 119 year: 2010 ident: B91 article-title: Crossing the Reality gap in Evolutionary Robotics by Promoting Transferable Controllers – start-page: 4397 year: 2015 ident: B56 article-title: Simulation Tools for Model-Based Robotics: Comparison of Bullet, Havok, Mujoco, ODE and Physx – volume-title: The Nature of Explanation year: 1943 ident: B39 – start-page: 2082 year: 2012 ident: B105 article-title: Adaptive Movement Sequences and Predictive Decisions Based on Hierarchical Dynamical Systems – start-page: 804 year: 2020 ident: B160 article-title: Encoding Physical Constraints in Differentiable newton-euler Algorithm – start-page: 4243 year: 2018 ident: B21 article-title: Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping – start-page: 1842 year: 2016 ident: B155 article-title: Meta-learning with Memory-Augmented Neural Networks – volume: 6 start-page: 325 year: 1997 ident: B76 article-title: Evolutionary Robotics and the Radical Envelope-Of-Noise Hypothesis publication-title: Adaptive Behav. doi: 10.1177/105971239700600205 – volume: 24 start-page: 47 year: 1999 ident: B109 article-title: Monte Carlo Bounding Techniques for Determining Solution Quality in Stochastic Programs publication-title: Operations Res. Lett. doi: 10.1016/S0167-6377(98)00054-6 – start-page: 837 year: 2019 ident: B133 article-title: Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows – start-page: 5307 year: 2015 ident: B121 article-title: Ensemble-cio: Full-Body Dynamic Motion Planning that Transfers to Physical Humanoids – start-page: 842 year: 2014 ident: B75 article-title: Tools for Simulating Humanoid Robot Dynamics: A Survey Based on User Feedback – year: 2019 ident: B128 article-title: Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning – volume: 24 start-page: 99 year: 2011 ident: B166 article-title: Bayesian Robot System Identification with Input and Output Noise publication-title: Neural Networks doi: 10.1016/j.neunet.2010.08.011 – volume: 74 start-page: 419 year: 2012 ident: B58 article-title: Constructing Summary Statistics for Approximate Bayesian Computation: Semi-automatic Approximate Bayesian Computation publication-title: J. R. Stat. Soc. doi: 10.1111/j.1467-9868.2011.01010.x – year: 2015 ident: B71 article-title: Distilling the Knowledge in a Neural Network – volume: 60 start-page: 1003 year: 2013 ident: B181 article-title: Lyapunov Stability and strong Passivity Analysis for Nonlinear Descriptor Systems publication-title: IEEE Trans. Circuits Syst. doi: 10.1109/TCSI.2012.2215396 – year: 2021 ident: B69 article-title: NeuralSim: Augmenting Differentiable Simulators with Neural Networks doi: 10.1109/ICRA48506.2021.9560935 – volume: 5 start-page: 101 year: 1986 ident: B10 article-title: Estimation of Inertial Parameters of Manipulator Loads and Links publication-title: Int. J. Robotics Res. doi: 10.1177/027836498600500306 – year: 2020 ident: B19 article-title: Learning Agile Robotic Locomotion Skills by Imitating Animals doi: 10.15607/RSS.2020.XVI.064 – year: 2017 ident: B184 article-title: Preparing for the Unknown: Learning a Universal Policy with Online System Identification doi: 10.15607/RSS.2017.XIII.048 – year: 2019 ident: B135 article-title: Fingerprint Policy Optimisation for Robust Reinforcement Learning – start-page: 07693 year: 2021 ident: B173 article-title: Stochastic Control through Approximate Bayesian Input Inference – year: 2020 ident: B2 article-title: Benchmarking Domain Randomisation for Visual Sim-To-Real Transfer – volume: 1 start-page: 263 year: 1953 ident: B83 article-title: Methods of Reducing Sample Size in Monte Carlo Computations publication-title: Or doi: 10.1287/opre.1.5.263 – start-page: 513 year: 2019 ident: B88 article-title: Self-paced Contextual Reinforcement Learning – volume: 84 start-page: 80 year: 2009 ident: B90 article-title: Continuous Global Optimization in Multiview 3d Reconstruction publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-009-0233-1 – volume: 100 start-page: 15324 year: 2003 ident: B112 article-title: Markov Chain Monte Carlo without Likelihoods publication-title: Proc. Natl. Acad. Sci. doi: 10.1073/pnas.0306899100 – start-page: 1126 year: 2017 ident: B60 article-title: Model-agnostic Meta-Learning for Fast Adaptation of Deep Networks – volume: 521 start-page: 503 year: 2015 ident: B42 article-title: Robots that Can Adapt like Animals publication-title: Nature doi: 10.1038/nature14422 – volume: 58 start-page: 595 year: 2010 ident: B51 article-title: Distributionally Robust Optimization under Moment Uncertainty with Application to Data-Driven Problems publication-title: Operations Res. doi: 10.1287/opre.1090.0741 – start-page: 3503 ident: B182 article-title: Sim-to-real Transfer for Biped Locomotion – year: 2018 ident: B164 article-title: Sim-to-real: Learning Agile Locomotion for Quadruped Robots doi: 10.15607/RSS.2018.XIV.010 – start-page: 3834 year: 2017 ident: B68 article-title: Grounded Action Transformation for Robot Learning in Simulation – volume: 34 start-page: 229 year: 2017 ident: B94 article-title: The DARPA Robotics challenge Finals: Results and Perspectives publication-title: J. Field Robotics doi: 10.1002/rob.21683 – start-page: 8973 year: 2019 ident: B31 article-title: Closing the Sim-To-Real Loop: Adapting Simulation Randomization with Real World Experience – year: 2017 ident: B73 article-title: Adversarial Attacks on Neural Network Policies, Workshop Track – volume: 27 start-page: 77 year: 1977 ident: B4 article-title: Dynamics of Pattern Formation in Lateral-Inhibition Type Neural fields publication-title: Biol. Cybern. doi: 10.1007/bf00337259 – start-page: 51 year: 2017 ident: B29 article-title: Black-box Data-Efficient Policy Search for Robotics – start-page: 2817 year: 2017 ident: B140 article-title: Robust Adversarial Reinforcement Learning – ident: B126 article-title: Neural Posterior Domain Randomization – volume: 13 start-page: 6 year: 2019 ident: B48 article-title: A Differentiable Physics Engine for Deep Learning in Robotics publication-title: Front. Neurorobot. doi: 10.3389/fnbot.2019.00006 – start-page: 6112 year: 2020 ident: B123 article-title: Learning Domain Randomization Distributions for Training Robust Locomotion Policies – start-page: 08324 year: 2019 ident: B47 article-title: Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation – year: 2014 ident: B163 article-title: Intriguing Properties of Neural Networks – start-page: 465 year: 2011 ident: B50 article-title: PILCO: a Model-Based and Data-Efficient Approach to Policy Search – start-page: 1162 year: 2019 ident: B116 article-title: Active Domain Randomization – start-page: 67 year: 1995 ident: B175 article-title: Adaptive Dual Control Methods: An Overview – volume: 2 start-page: 160 year: 1991 ident: B161 article-title: Dyna, an Integrated Architecture for Learning, Planning, and Reacting publication-title: SIGART Bull. doi: 10.1145/122344.122377 – volume: 7 start-page: 303 year: 1979 ident: B86 article-title: Existence and Stability of Local Excitations in Homogeneous Neural fields publication-title: J. Math. Biol. doi: 10.1007/bf00275151 – start-page: August 11 year: 2017 ident: B102 article-title: Stein Variational Policy Gradient – volume: 37 start-page: 421 year: 2018 ident: B100 article-title: Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection publication-title: Int. J. Robotics Res. doi: 10.1177/0278364917710318 – volume: 17 start-page: 122 year: 2013 ident: B92 article-title: The Transferability Approach: Crossing the Reality gap in Evolutionary Robotics publication-title: IEEE Trans. Evol. Computat. doi: 10.1109/TEVC.2012.2185849 – year: 2020 ident: B66 article-title: Perspectives on Sim2real Transfer for Robotics: A Summary of the R:SS 2020 Workshop – volume: 25 start-page: 649 year: 1979 ident: B176 article-title: On the Effectiveness of Common Random Numbers publication-title: Manag. Sci. doi: 10.1287/mnsc.25.7.649 – year: 2017 ident: B154 article-title: CAD2RL: Real Single-Image Flight without a Single Real Image doi: 10.15607/RSS.2017.XIII.034 – year: 2021 ident: B46 article-title: Lyapunov-stable Neural-Network Control doi: 10.15607/RSS.2021.XVII.063 – volume: 2 start-page: 33 year: 1963 ident: B33 article-title: On Optimal Stopping Rules publication-title: Z. Wahrscheinlichkeitstheorie Verw Gebiete doi: 10.1007/bf00535296 – start-page: 15388 year: 2021 ident: B1 article-title: Distributionally Robust Trajectory Optimization under Uncertain Dynamics via Relative-Entropy Trust Regions – start-page: 406 year: 2000 ident: B129 article-title: PEGASUS: a Policy Search Method for Large Mdps and Pomdps – volume: 110 start-page: 18327 year: 2013 ident: B14 article-title: Simulation as an Engine of Physical Scene Understanding publication-title: Proc. Natl. Acad. Sci. doi: 10.1073/pnas.1306572110 – start-page: 742 year: 2017 ident: B32 article-title: Learning Efficient Object Detection Models with Knowledge Distillation – volume-title: Robust Value Iteration for Continuous Control Tasks ident: B106 doi: 10.15607/RSS.2021.XVII.007 – volume: 27 start-page: 262 year: 2016 ident: B35 article-title: Predictable Behavior during Contact Simulation: a Comparison of Selected Physics Engines publication-title: Comp. Anim. Virtual Worlds doi: 10.1002/cav.1712 – year: 2019 ident: B149 article-title: Learning to Simulate – start-page: 3 year: 2017 ident: B27 article-title: Adversarial Examples Are Not Easily Detected – start-page: 35 year: 2018 ident: B103 article-title: Reinforcement Learning for Non-prehensile Manipulation: Transfer from Simulation to Physical System – start-page: 4383 year: 2020 ident: B85 article-title: Sim2real Transfer for Reinforcement Learning without Dynamics Randomization – volume: 2 start-page: 1 year: 2011 ident: B49 article-title: A Survey on Policy Search for Robotics publication-title: FNT in Robotics doi: 10.1561/2300000021 – start-page: 12627 year: 2019 ident: B79 article-title: Sim-to-real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks – year: 2017 ident: B171 article-title: Learning to Reinforcement Learn – volume: 21 start-page: 1240 year: 1960 ident: B59 article-title: Dual Control Theory. I publication-title: Avtomatika i Telemekhanika – start-page: 12864 volume-title: Predicting Sim-To-Real Transfer with Probabilistic Dynamics Models year: 2020 ident: B186 – year: 2016 ident: B22 article-title: Openai Gym – start-page: 262 year: 2017 ident: B153 article-title: Sim-to-real Robot Learning from Pixels with Progressive Nets – start-page: 704 year: 1995 ident: B77 article-title: Noise and the Reality gap: The Use of Simulation in Evolutionary Robotics – volume: 518 start-page: 529 year: 2015 ident: B119 article-title: Human-level Control through Deep Reinforcement Learning publication-title: Nature doi: 10.1038/nature14236 – volume: 6 start-page: 911 ident: B124 article-title: Data-efficient Domain Randomization with Bayesian Optimization publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2021.3052391 |
| SSID | ssj0001584377 |
| Score | 2.532296 |
| SecondaryResourceType | review_article |
| Snippet | The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 799893 |
| SubjectTerms | domain randomization reality gap reinforcement learning robotics Robotics and AI simulation simulation optimization bias |
| Title | Robot Learning From Randomized Simulations: A Review |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/35494543 https://www.proquest.com/docview/2658652040 https://pubmed.ncbi.nlm.nih.gov/PMC9038844 https://doaj.org/article/1210b94d63c44ba5bbde7a81cea090af |
| Volume | 9 |
| WOSCitedRecordID | wos000792457300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2296-9144 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001584377 issn: 2296-9144 databaseCode: DOA dateStart: 20140101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2296-9144 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001584377 issn: 2296-9144 databaseCode: M~E dateStart: 20140101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELag4gAHVN4LpQoSJ6RQJ57Edm8t6ooDVKg8tDfL4wesxCZod8uBA7-dcZyudhGCC5ccEkeZfBN75tM43zD2POpoIYS2jL6FElTtSmy4oETOO08RqfWDlNKnN_L8XM1m-t1Wq6-0JyzLA2fgjpLAFWrwrXAAaBtEH6RVlQuWa25jWn0p69kiU_n_YAVCylzGJBamj-Kyx7R3sq5fSqIYWuwEokGv_09J5u97JbeCz3Sf3R6zxuIkW3uHXQvdXXZrS0vwHoOLHvt1Meqlfi6my35RXNjO94v5j-CL9_PF2KlrdVycFLkmcJ99nJ59ePW6HFsilI4my7oE5I47oBcX1qHn3GINCAK5ilHVCJr4YBWiQl-1IRDVFAKVQ2Eltk7W4gHb6_ouPGJFaBoVKRmh-I_ggrJKeyWsx-hEtBonjF_hY9yoF57aVnw1xBsSpGaA1CRITYZ0wl5sbvmWxTL-Nvg0gb4ZmHSuhxPkfTN63_zL-xP27MplhuZFKnbYLvSXK1NTatU2Na1RE_Ywu3DzKEGkGBogE-SOc3ds2b3Szb8M2ts6qecAPP4fxj9hNxMeqTZVVQdsb728DE_ZDfd9PV8tD9l1OVOHw2dNx7c_z34BLCb_mQ |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Robot+Learning+From+Randomized+Simulations%3A+A+Review&rft.jtitle=Frontiers+in+robotics+and+AI&rft.au=Muratore%2C+Fabio&rft.au=Ramos%2C+Fabio&rft.au=Turk%2C+Greg&rft.au=Yu%2C+Wenhao&rft.date=2022-04-11&rft.eissn=2296-9144&rft.volume=9&rft.spage=799893&rft_id=info:doi/10.3389%2Ffrobt.2022.799893&rft_id=info%3Apmid%2F35494543&rft.externalDocID=35494543 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-9144&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-9144&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-9144&client=summon |