Abstract
We have proposed an online policy-improving system of reinforcement learning (RL) agents with a mixture model of Bayesian Networks (BNs), and discussed properties of the system. In this paper, two types of mixture models have been applied to the system. A structure of BN in the mixture model is selected based on data collected by agents in an environment, and is regarded as a stochastic knowledge of the environment. This research investigates the adaptability of our system to dynamic environments containing an unexperienced environment, in which an agent does not have the knowledge.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Forbes, J., Huang, T., Kanazawa, K., Russell, S.: The MATmobile: Towards a Bayesian Automated Taxi. In: Proc. of the 14th Int. Joint Conf. on Artificial Intelligence, pp. 1878–1885 (1995)
Kitakoshi, D., Shioya, H., Kurihara, M.: Analysis of a Method Improving Reinforcement Learning Agents’ Policies. Journal of ACIII 7(3), 276–282 (2003)
Kitakoshi, D., Shioya, H., Kurihara, M.: A Reinforcement Learning System by using a Mixture Model of Bayesian Network. In: SICE Annual Conference 2003 Proc. TAII-14-1 (2003) (CD-ROM)
Heckerman, D.: A Tutorial on Learning with Bayesian Networks. Technical Report MSR-TR-95-06, Microsoft Research (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kitakoshi, D., Shioya, H., Nakano, R. (2005). Analysis for Adaptability of Policy-Improving System with a Mixture Model of Bayesian Networks to Dynamic Environments. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3684. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11554028_102
Download citation
DOI: https://doi.org/10.1007/11554028_102
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28897-8
Online ISBN: 978-3-540-31997-9
eBook Packages: Computer ScienceComputer Science (R0)