20 citations · 150 across the 43 of their papers we have counts for
11 papers · 1 filter
Training Larger Networks for Deep Reinforcement Learning
Kei Ota, Devesh K. Jha, Asako Kanezaki
The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions…
Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation
Kei Ota, Devesh K. Jha, Diego Romeres +7
Humans quickly solve tasks in novel systems with complex dynamics, without requiring much interaction. While deep reinforcement learning algorithms have achieved tremendous success…
Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path
Kei Ota, Yoko Sasaki, Devesh K. Jha +2
In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can ef…
CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context
Wenyu Zhang, Skyler Seto, Devesh K. Jha
Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with unknown workp…
Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
Kei Ota, Tomoaki Oiki, Devesh K. Jha +2
Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes in various sequential decision making tasks, leveraging advances in methods for training lar…
Model-Based Reinforcement Learning for Physical Systems Without Velocity and Acceleration Measurements
Alberto Dalla Libera, Diego Romeres, Devesh K. Jha +2
In this paper, we propose a derivative-free model learning framework for Reinforcement Learning (RL) algorithms based on Gaussian Process Regression (GPR). In many mechanical syste…
Multi-label Prediction in Time Series Data using Deep Neural Networks
Wenyu Zhang, Devesh K. Jha, Emil Laftchiev +1
This paper addresses a multi-label predictive fault classification problem for multidimensional time-series data. While fault (event) detection problems have been thoroughly studie…
Local Policy Optimization for Trajectory-Centric Reinforcement Learning
Patrik Kolaric, Devesh K. Jha, Arvind U. Raghunathan +4
The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based re…
Quasi-Newton Trust Region Policy Optimization
Devesh Jha, Arvind Raghunathan, Diego Romeres
We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradi…
Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function
Arvind U. Raghunathan, Anoop Cherian, Devesh K. Jha
Computing Nash equilibrium (NE) of multi-player games has witnessed renewed interest due to recent advances in generative adversarial networks. However, computing equilibrium effic…
Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics
Jeroen van Baar, Alan Sullivan, Radu Cordorel +3
Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can…