Showing 2023Show all
2 papers · 1 filter
eess.SY2023
Controllability-Constrained Deep Network Models for Enhanced Control of Dynamical Systems
Suruchi Sharma, Volodymyr Makarenko, Gautam Kumar +1
Control of a dynamical system without the knowledge of dynamics is an important and challenging task. Modern machine learning approaches, such as deep neural networks (DNNs), allow…
cs.LG2023
Bounding the Optimal Value Function in Compositional Reinforcement Learning
Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas +2
In the field of reinforcement learning (RL), agents are often tasked with solving a variety of problems differing only in their reward functions. In order to quickly obtain solutio…