Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Assayag, G., Bloch, G., Chemillier, M., Caen, U.D.: Omax-ofon. In: 3th Sound and Music Computing Conference, Marseille, France (2006)
Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Optimization and Neural Computation Series. Athena Scientific, Belmont (1996)
Bickerman, G., Bosley, S., Swire, P., Keller, R.: Learning to play jazz with deep belief networks. In: Proceedings of the International Conference on Computational Creativity, pp. 228–237. University of Coimbra, Portugal (2010)
Collins, N.: The potential of reinforcement learning for live musical agents. In: International Machine Workshop on Machine Learning and Music, International Conference on Machine Learning, University of Helsinki, Finland (2008)
Daly, M.: Sheet music digital (2010), http://www.sheetmusicdigital.com/ (accessed February 8, 2014)
Daw, N.D., Kakade, S., Dayan, P.: Opponent interactions between serotonin and dopamine. Neural Networks 15(4-6), 603–616 (2002)
Dayan, P.: Goal-directed control and its antipodes. Neural Networks 22(3), 213–219 (2009)
Doornbusch, P.: The music of CSIRAC: Australia’s first computer music. Common Ground Publishing, Altona (2005)
Doya, K.: Metalearning, neuromodulation and emotion. In: Hatano, G. (ed.) Proceedings of the 13th Toyota Conference on Affective Minds, pp. 101–104. Elsevier Science, B.V. (2000)
Doya, K.: Metalearning and neuromodulation. Neural Networks 15(4-6), 495–506 (2002)
Doya, K.: Modulators of decision making. Nature Neuroscience 11, 410–416 (2008)
Franklin, J.: Recurrent neural networks for music computation. INFORMS Journal on Computing 18(3), 321–338 (2006)
Franklin, J.A., Manfredi, V.U.: Nonlinear credit assignment for musical sequences. In: Abraham, A., Nath, B., Sambandham, M., Saratchandran, P. (eds.) Computational Intelligence and Applications—Second International Workshop on Intelligent Systems Design and Application, pp. 245–250. Dynamic Publishers, Inc., Atlanta (2002)
Groux, S.L., Verschure, P.F.M.J.: Towards adaptive music generation by reinforcement learning of musical tension. In: 7th Sound and Music Computing Conference, Barcelona, Spain (2010)
Hiller, L., Isaacson, L.: Experimental Music - Composition with an Electronic Computer. McGraw-Hill Book Co. (1959)
Mammarella, N., Fairfield, B., Cornoldi, C.: Does music enhance cognitive performance in healthy older adults? The Vivaldi effect. Aging Clinical and Experimental Research 19(5), 394–399 (2007)
Muller, H.J.: A simple formula giving the number of individuals required for obtaining one of a given frequency. The American Naturalist 57(648), 66–73 (1923)
Rauscher, F.H., Shaw, G.L., Ky, K.N.: Music and spatial task performance. Nature 365(6447), 611 (1993)
Schweighofer, N., Doya, K.: Meta-learning in reinforcement learning. Neural Networks 16(1), 5–9 (2003)
Smith, B.D., Garnett, G.E.: Reinforcement learning and the creative, automated music improviser. In: Machado, P., Romero, J., Carballal, A. (eds.) EvoMUSART 2012. LNCS, vol. 7247, pp. 223–234. Springer, Heidelberg (2012)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. In: Adaptive Computation and Machine Learning, The MIT Press, Cambridge (1998)
Xenakis, I.: Formalised Music: Thought and Mathematics in Composition., 2nd edn. Pendragon Press, Stuyvesant (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Walker, J., Chalup, S.K. (2015). Learning Nursery Rhymes Using Adaptive Parameter Neurodynamic Programming. In: Chalup, S.K., Blair, A.D., Randall, M. (eds) Artificial Life and Computational Intelligence. ACALCI 2015. Lecture Notes in Computer Science(), vol 8955. Springer, Cham. https://doi.org/10.1007/978-3-319-14803-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-14803-8_16
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14802-1
Online ISBN: 978-3-319-14803-8
eBook Packages: Computer ScienceComputer Science (R0)