Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Roberto Calandra

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning


Feb 26, 2021
Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra

* 19 pages, accepted by AISTATS 2021 

  Access Paper or Ask Questions

Model-Invariant State Abstractions for Model-Based Reinforcement Learning


Feb 19, 2021
Manan Tomar, Amy Zhang, Roberto Calandra, Matthew E. Taylor, Joelle Pineau


  Access Paper or Ask Questions

Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning


Dec 16, 2020
Nathan O. Lambert, Albert Wilcox, Howard Zhang, Kristofer S. J. Pister, Roberto Calandra

* 8 pages, +2 pages appendix 

  Access Paper or Ask Questions

TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors


Dec 15, 2020
Shaoxiong Wang, Mike Lambeta, Po-Wei Chou, Roberto Calandra


  Access Paper or Ask Questions

Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion


Sep 18, 2020
Tianyu Li, Roberto Calandra, Deepak Pathak, Yuandong Tian, Franziska Meier, Akshara Rai


  Access Paper or Ask Questions

Active MR k-space Sampling with Reinforcement Learning


Jul 20, 2020
Luis Pineda, Sumana Basu, Adriana Romero, Roberto Calandra, Michal Drozdzal

* To appear in 23rd International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2020 

  Access Paper or Ask Questions

3D Shape Reconstruction from Vision and Touch


Jul 07, 2020
Edward J. Smith, Roberto Calandra, Adriana Romero, Georgia Gkioxari, David Meger, Jitendra Malik, Michal Drozdzal

* Submitted for review 

  Access Paper or Ask Questions

Learning Invariant Representations for Reinforcement Learning without Reconstruction


Jun 18, 2020
Amy Zhang, Rowan McAllister, Roberto Calandra, Yarin Gal, Sergey Levine


  Access Paper or Ask Questions

Learning to Play Table Tennis From Scratch using Muscular Robots


Jun 10, 2020
Dieter Büchler, Simon Guist, Roberto Calandra, Vincent Berenz, Bernhard Schölkopf, Jan Peters

* 11 pages, 8 figures. Submitted to T-RO. For more information visit https://muscularTT.embodied.ml 

  Access Paper or Ask Questions

DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation


May 29, 2020
Mike Lambeta, Po-Wei Chou, Stephen Tian, Brian Yang, Benjamin Maloon, Victoria Rose Most, Dave Stroud, Raymond Santos, Ahmad Byagowi, Gregg Kammerer, Dinesh Jayaraman, Roberto Calandra

* 8 pages, published in the IEEE Robotics and Automation Letters (RA-L) 

  Access Paper or Ask Questions

Plan2Vec: Unsupervised Representation Learning by Latent Plans


May 07, 2020
Ge Yang, Amy Zhang, Ari S. Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra

* Proceedings of Machine Learning Research, the 2nd Annual Conference on Learning for Dynamics and Control (2020) Volume 120, 1-12 
* code available at https://geyang.github.io/plan2vec 

  Access Paper or Ask Questions

Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads


Apr 23, 2020
Suneel Belkhale, Rachel Li, Gregory Kahn, Rowan McAllister, Roberto Calandra, Sergey Levine


  Access Paper or Ask Questions

Adversarial Continual Learning


Mar 21, 2020
Sayna Ebrahimi, Franziska Meier, Roberto Calandra, Trevor Darrell, Marcus Rohrbach


  Access Paper or Ask Questions

OmniTact: A Multi-Directional High Resolution Touch Sensor


Mar 16, 2020
Akhil Padmanabha, Frederik Ebert, Stephen Tian, Roberto Calandra, Chelsea Finn, Sergey Levine

* Accepted at International Conference on Robotics and Automation (ICRA) 2020 

  Access Paper or Ask Questions

Objective Mismatch in Model-based Reinforcement Learning


Feb 11, 2020
Nathan Lambert, Brandon Amos, Omry Yadan, Roberto Calandra

* 8 pages, 2 pages references, 5 pages appendices 

  Access Paper or Ask Questions

Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization


Jan 31, 2020
Benjamin Letham, Roberto Calandra, Akshara Rai, Eytan Bakshy


  Access Paper or Ask Questions

Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning


Nov 15, 2019
Kevin Sebastian Luck, Heni Ben Amor, Roberto Calandra

* Accepted for the Conference on Robot Learning 2019 

  Access Paper or Ask Questions

Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning


Sep 26, 2019
Tianyu Li, Nathan Lambert, Roberto Calandra, Franziska Meier, Akshara Rai

* Submitted to 2020 ICRA 

  Access Paper or Ask Questions

Data-efficient Learning of Morphology and Controller for a Microrobot


May 03, 2019
Thomas Liao, Grant Wang, Brian Yang, Rene Lee, Kristofer Pister, Sergey Levine, Roberto Calandra

* Accepted at ICRA-2019. 6 pages 

  Access Paper or Ask Questions

Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots


Apr 07, 2019
Dieter Büchler, Roberto Calandra, Jan Peters

* 12 pages, preprint submitted to Journal of Robotics and Autonomous Systems 

  Access Paper or Ask Questions

Manipulation by Feel: Touch-Based Control with Deep Predictive Models


Mar 11, 2019
Stephen Tian, Frederik Ebert, Dinesh Jayaraman, Mayur Mudigonda, Chelsea Finn, Roberto Calandra, Sergey Levine

* Accepted to ICRA 2019 

  Access Paper or Ask Questions

Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matching


Mar 08, 2019
Justin Lin, Roberto Calandra, Sergey Levine

* 6 pages; accepted to IEEE International Conference on Robotics and Automation 2019 (ICRA 2019) 

  Access Paper or Ask Questions

Fast Neural Network Verification via Shadow Prices


Mar 08, 2019
Vicenc Rubies-Royo, Roberto Calandra, Dusan M. Stipanovic, Claire Tomlin


  Access Paper or Ask Questions

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement learning


Jan 11, 2019
Nathan O. Lambert, Daniel S. Drew, Joseph Yaconelli, Roberto Calandra, Sergey Levine, Kristofer S. J. Pister

* 10 pages, 12 figures 

  Access Paper or Ask Questions

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models


Nov 02, 2018
Kurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine

* NIPS 2018, video and code available at https://sites.google.com/view/drl-in-a-handful-of-trials/ 

  Access Paper or Ask Questions

More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch


Jul 26, 2018
Roberto Calandra, Andrew Owens, Dinesh Jayaraman, Justin Lin, Wenzhen Yuan, Jitendra Malik, Edward H. Adelson, Sergey Levine

* 8 pages. Published on IEEE Robotics and Automation Letters (RAL). Website: https://sites.google.com/view/more-than-a-feeling 

  Access Paper or Ask Questions

Learning Flexible and Reusable Locomotion Primitives for a Microrobot


Mar 01, 2018
Brian Yang, Grant Wang, Roberto Calandra, Daniel Contreras, Sergey Levine, Kristofer Pister

* 8 pages. Accepted at RAL+ICRA2018 

  Access Paper or Ask Questions

MBMF: Model-Based Priors for Model-Free Reinforcement Learning


Oct 17, 2017
Somil Bansal, Roberto Calandra, Kurtland Chua, Sergey Levine, Claire Tomlin

* After we submitted the paper for consideration in CoRL 2017 we found a paper published in the recent past with a similar method (see related work for a discussion). Considering the similarities between the two papers, we have decided to retract our paper from CoRL 2017 

  Access Paper or Ask Questions