Learning nursery rhymes using adaptive parameter neurodynamic programming

Title: Learning nursery rhymes using adaptive parameter neurodynamic programming
Creator: Walker, Josiah; Chalup, Stephan K.
Relation: Australasian Conference on Artificial Life and Computational Intelligence (ACALCI 2015). Proceedings of the Australasian Conference on Artificial Life and Computational Intelligence (Newcastle, N.S.W. 5-7 February, 2015) p. 196-209
Publisher Link: http://dx.doi.org/10.1007/978-3-319-14803-8_16
Publisher: Springer
Resource Type: conference paper
Date: 2015
Description: In this study on music learning, we develop an average reward based adaptive parameterisation for reinforcement learning meta-parameters. These are tested using an approximation of user feedback based on the goal of learning the nursery rhymes Twinkle Twinkle Little Star and Mary Had a Little Lamb. We show that a large reduction in learning times can be achieved through a combination of adaptive parameters and random restarts to ensure policy convergence.
Subject: neuro-dynamic programming; reinforcement learning; meta-parameters; online music learning
Identifier: http://hdl.handle.net/1959.13/1334366
Identifier: uon:27277
Identifier: ISBN:9783319148021
Language: eng
Reviewed

		Thumbnail	File	Description	Size	Format