8 citations · 34 across the 14 of their papers we have counts for
8 papers · 1 filter
Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning
Xinjie Liu, Ruihan Zhao, Anirban Chaudhuri +3
Policy gradient methods for on-policy reinforcement learning (RL) can become unstable when expensive, scarce target-domain data yield noisy gradient estimates. We address this chal…
A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation
Xinjie Liu, Cyrus Neary, Kushagra Gupta +4
Many reinforcement learning (RL) algorithms are impractical for training in operational systems or computationally expensive high-fidelity simulations, as they require large amount…
Neural Port-Hamiltonian Differential Algebraic Equations for Compositional Learning of Electrical Networks
Cyrus Neary, Nathan Tsao, Ufuk Topcu
We develop compositional learning algorithms for coupled dynamical systems, with a particular focus on electrical networks. While deep learning has proven effective at modeling com…
How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations
Franck Djeumou, Cyrus Neary, Ufuk Topcu
We present a framework and algorithms to learn controlled dynamics models using neural stochastic differential equations (SDEs) -- SDEs whose drift and diffusion terms are both par…
Compositional Learning of Dynamical System Models Using Port-Hamiltonian Neural Networks
Cyrus Neary, Ufuk Topcu
Many dynamical systems -- from robots interacting with their surroundings to large-scale multiphysics systems -- involve a number of interacting subsystems. Toward the objective of…
Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs
Franck Djeumou, Cyrus Neary, Eric Goubault +2
Neural ordinary differential equations (NODEs) -- parametrizations of differential equations using neural networks -- have shown tremendous promise in learning models of unknown co…
Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling
Franck Djeumou, Cyrus Neary, Eric Goubault +2
Effective inclusion of physics-based knowledge into deep neural network models of dynamical systems can greatly improve data efficiency and generalization. Such a-priori knowledge…
Verifiable and Compositional Reinforcement Learning Systems
Cyrus Neary, Christos Verginis, Murat Cubuktepe +1
We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, a…