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 Devesh K. Jha

Distributed Task Allocation in Homogeneous Swarms Using Language Measure Theory


Jun 25, 2021
Devesh K. Jha

* Under review 

  Access Paper or Ask Questions

Trajectory Optimization for Manipulation of Deformable Objects: Assembly of Belt Drive Units


Jun 21, 2021
Shiyu Jin, Diego Romeres, Arvind Ragunathan, Devesh K. Jha, Masayoshi Tomizuka


  Access Paper or Ask Questions

PYROBOCOP : Python-based Robotic Control & Optimization Package for Manipulation and Collision Avoidance


Jun 06, 2021
Arvind U. Raghunathan, Devesh K. Jha, Diego Romeres

* Under review at IJRR 

  Access Paper or Ask Questions

Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry


Apr 02, 2021
Siyuan Dong, Devesh K. Jha, Diego Romeres, Sangwoon Kim, Daniel Nikovski, Alberto Rodriguez


  Access Paper or Ask Questions

Markov Modeling of Time-Series Data using Symbolic Analysis


Mar 23, 2021
Devesh K. Jha


  Access Paper or Ask Questions

Training Larger Networks for Deep Reinforcement Learning


Feb 16, 2021
Kei Ota, Devesh K. Jha, Asako Kanezaki

* Under submission 

  Access Paper or Ask Questions

Towards Human-Level Learning of Complex Physical Puzzles


Nov 14, 2020
Kei Ota, Devesh K. Jha, Diego Romeres, Jeroen van Baar, Kevin A. Smith, Takayuki Semitsu, Tomoaki Oiki, Alan Sullivan, Daniel Nikovski, Joshua B. Tenenbaum

* 10 pages, 7 figures 

  Access Paper or Ask Questions

Deep Reactive Planning in Dynamic Environments


Nov 05, 2020
Kei Ota, Devesh K. Jha, Tadashi Onishi, Asako Kanezaki, Yusuke Yoshiyasu, Yoko Sasaki, Toshisada Mariyama, Daniel Nikovski

* 15 pages, 5 figures. Accepted at CoRL 2020 

  Access Paper or Ask Questions

Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks


Jul 22, 2020
Yifang Liu, Diego Romeres, Devesh K. Jha, Daniel Nikovski

* Published at a RSS20 workshop 

  Access Paper or Ask Questions

CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context


Mar 26, 2020
Wenyu Zhang, Skyler Seto, Devesh K. Jha


  Access Paper or Ask Questions

Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path


Mar 03, 2020
Kei Ota, Yoko Sasaki, Devesh K. Jha, Yusuke Yoshiyasu, Asako Kanezaki

* 8 pages, 10 figures 

  Access Paper or Ask Questions

Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?


Mar 03, 2020
Kei Ota, Tomoaki Oiki, Devesh K. Jha, Toshisada Mariyama, Daniel Nikovski

* 11 pages, 10 figures 

  Access Paper or Ask Questions

Model-Based Reinforcement Learning for Physical Systems Without Velocity and Acceleration Measurements


Feb 25, 2020
Alberto Dalla Libera, Diego Romeres, Devesh K. Jha, Bill Yerazunis, Daniel Nikovski

* Accepted at RA-L 

  Access Paper or Ask Questions

Multi-label Prediction in Time Series Data using Deep Neural Networks


Jan 27, 2020
Wenyu Zhang, Devesh K. Jha, Emil Laftchiev, Daniel Nikovski

* Accepted by IJPHM. Presented at PHM19 

  Access Paper or Ask Questions

Local Policy Optimization for Trajectory-Centric Reinforcement Learning


Jan 22, 2020
Patrik Kolaric, Devesh K. Jha, Arvind U. Raghunathan, Frank L. Lewis, Mouhacine Benosman, Diego Romeres, Daniel Nikovski

* ICRA 2020 

  Access Paper or Ask Questions

Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation


Jul 03, 2019
Ankush Chakrabarty, Devesh K. Jha, Gregery T. Buzzard, Yebin Wang, Kyriakos Vamvoudakis


  Access Paper or Ask Questions

Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function


May 15, 2019
Arvind U. Raghunathan, Anoop Cherian, Devesh K. Jha

* Accepted at International Conference on Machine Learning (ICML), 2019 

  Access Paper or Ask Questions

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning


Mar 13, 2019
Kei Ota, Devesh K. Jha, Tomoaki Oiki, Mamoru Miura, Takashi Nammoto, Daniel Nikovski, Toshisada Mariyama

* 8 pages, 6 figures 

  Access Paper or Ask Questions