On the Role of Models in Learning Control: Actor-Critic Iterative Learning Control
Year: 2020
Type: conference-paper
Abstract: Learning from data of past tasks can substantially improve the accuracy of mechatronic systems. Often, for fast and safe learning a model of the system is required. The aim of this paper is to develop a model-free approach for fast and safe learning for mechatronic systems. The developed actor-critic iterative learning control (ACILC) framework uses a feedforward parameterization with basis functions. These basis functions encode implicit model knowledge and the actor-critic algorithm learns the feedforward parameters without explicitly using a model. Experimental results on a printer setup demonstrate that the developed ACILC framework is capable of achieving the same feedforward signal as preexisting model-based methods without using explicit model knowledge.
Source: TU/e Research Portal
Authors: Poot, M.M., Portegies, Jim, Oomen, Tom, Carloni, Raffaella, Jayawardhana, Bayu, Lefeber, Erjen
Institution: Eindhoven University of Technology
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3095672017
