Abstract
In this paper, the use of two internal reward models, curiosity and boredom, is proposed. Experiments on a maze navigation task demonstrated that appropriate values of parameters simultaneously improved the performance of the predictor of the environment and increase the external rewards compared with the conventional reinforcement learning. In conclusions, the relation between the proposed method and active learning, diversive curiosity, and specific curiosity is also discussed.
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
Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Cambridge (1998)
Shmidhuber, J.: Self-motivated development through rewards for predictor errors / improvements. In: Developmental Robotics, 2005 AAAI Spring Symposium (2005)
Oudeyer, P.-Y., Kaplan, F., Hafner, V.V.: Intrinsic Motivation Systems for Autonomous Mental Development. IEEE Trans. EC 11(2), 265–286 (2007)
Stout, A., Konidaris, G.D., Barto, A.G.: Intrinsically motivated reinforcement learning: A promising framework for developmental robot learning. In: Developmental Robotics AAAI Spring Symp. (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Yamamoto, N., Ishikawa, M. (2010). Curiosity and Boredom Based on Prediction Error as Novel Internal Rewards. In: Hanazawa, A., Miki, T., Horio, K. (eds) Brain-Inspired Information Technology. Studies in Computational Intelligence, vol 266. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04025-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-04025-2_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04024-5
Online ISBN: 978-3-642-04025-2
eBook Packages: EngineeringEngineering (R0)