Optimal Observer Design Using Reinforcement Learning and Quadratic Neural Networks

no code implementations • 27 Nov 2023 • Soroush Asri, Luis Rodrigues

It is proven that the obtained linear correction term is optimal for linear systems, as both the value function and the QNN's input-output mapping are quadratic.

reinforcement-learning Reinforcement Learning (RL)

Data-Driven LQR using Reinforcement Learning and Quadratic Neural Networks

no code implementations • 16 Nov 2023 • Soroush Asri, Luis Rodrigues

This paper introduces a novel data-driven approach to design a linear quadratic regulator (LQR) using a reinforcement learning (RL) algorithm that does not require a system model.

reinforcement-learning Reinforcement Learning (RL)