A small spiking neural network with LQR control applied to the acrobot
Wiklendt, Lukasz and Chalup, Stephan and Middleton, Rick (2009) A small spiking neural network with LQR control applied to the acrobot. Neural Computing & Applications , 18 (4). pp. 369-375. ISSN 1433-3058
This paper presents the results of a computer simulation which, combined a small network of spiking neurons with linear quadratic regulator (LQR) control to solve the acrobot swing-up and balance task. To our knowledge, this task has not been previously solved with spiking neural networks. Input to the network was drawn from the state of the acrobot, and output was torque, either directly applied to the actuated joint, or via the switching of an LQR controller designed for balance. The neural network’s weights were tuned using a (µ λ)-evolution strategy without recombination, and neurons’ parameters, were chosen to roughly approximate biological neurons.
Repository Staff Only: item control page