{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T17:24:33Z","timestamp":1783013073247,"version":"3.54.6"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001409","name":"DST","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001409","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007780","name":"IISc","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812089","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"1631-1637","source":"Crossref","is-referenced-by-count":3,"title":["Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning"],"prefix":"10.1109","author":[{"given":"Utkarsh A.","family":"Mishra","sequence":"first","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soumya R.","family":"Samineni","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prakhar","family":"Goel","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology,Electronics and Communication Engineering Department,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chandravaran","family":"Kunjeti","sequence":"additional","affiliation":[{"name":"National Institute of Technology,Electronics and Communication Engineering Department,Karnataka,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Himanshu","family":"Lodha","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aman","family":"Singh","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditya","family":"Sagi","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shishir","family":"Kolathaya","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"janner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"lowrey","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561298"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.033"},{"key":"ref14","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref15","article-title":"Learning stable deep dynamics models","volume":"32","author":"kolter","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"ICLR (Poster)"},{"key":"ref17","first-page":"579","article-title":"Dynamical models and tracking regret in online convex programming","author":"hall","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref18","year":"0","journal-title":"Appendix"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref4","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref6","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","author":"nagabandi","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref8","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref7","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.064"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref20","author":"coumans","year":"2016","journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning"},{"key":"ref22","author":"paigwar","year":"2020","journal-title":"Robust quadrupedal locomotion on sloped terrains A linear policy approach"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref23","article-title":"Learning to walk via deep reinforcement learning","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812089.pdf?arnumber=9812089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:06:56Z","timestamp":1667516816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812089","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}