Abstract
We propose a new approach for estimating the difference between two partially observable dynamical systems. We assume that one can interact with the systems by performing actions and receiving observations. The key idea is to define a Markov Decision Process (MDP) based on the systems to be compared, in such a way that the optimal value of the MDP initial state can be interpreted as a divergence (or dissimilarity) between the systems. This dissimilarity can then be estimated by reinforcement learning methods. Moreover, the optimal policy will contain information about the actions which most distinguish the systems. Empirical results show that this approach is useful in detecting both big and small differences, as well as in comparing systems with different internal structure.
Chapter PDF
References
Desharnais, J., Laviolette, F., Zhioua, S.: Testing probabilistic equivalence through reinforcement learning. In: Arun-Kumar, S., Garg, N. (eds.) FSTTCS 2006. LNCS, vol. 4337, pp. 236–247. Springer, Heidelberg (2006)
Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial Intelligence 101, 99–134 (1998)
Larsen, K.G., Skou, A.: Bisimulation through probabilistic testing. Inf. Comput. 94, 1–28 (1991)
Singh, S., James, M., Rudary, M.: Predictive state representations: a new theory for modeling dynamical systems. In: The 20th Conference on Uncertainty in Artificial Intelligence, Banff, Canada, pp. 512–519 (2004)
Cover, T.M., Thomas, J.A.: 12. In: Elements of Information Theory. Wiley, Chichester (1991)
Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)
Kearns, M.J., Mansour, Y., Ng, A.Y.: A sparse sampling algorithm for near-optimal planning in large markov decision processes. Machine Learning 49, 193–208 (2002)
Cassandra, T.: Tony’s POMDP Page (2009), http://www.cs.brown.edu/research/ai/pomdp/
Hoey, J., Bertoldi, A., Poupart, P., Mihailidis, A.: Assisting persons with dementia during handwashing using a partially observable markov decision process. In: The 5th International Conference on Computer Vision Systems, Bielefeld, March 21-24 (2007)
Desharnais, J., Gupta, V., Jagadeesan, R., Panangaden, P.: Metrics for labeled Markov processes. Theoretical Computer Science 318, 323–354 (2004)
Ferns, N., Castro, P., Panangaden, P., Precup, D.: Methods for computing state similarity in markov decision processes. In: Proceedings of the 22nd Conference on Uncertainty in Artificial intelligence, Cambridge, MA, USA, July 13 - 16 (2006)
Levinson, S., Rabiner, L.: An introduction to the application of the theory of probabilistic functions of a return process to automatic speech recognition. The Bell System Technical Journal 62, 1035–1074 (1983)
Juang, B., Rabiner, L.: A probabilistic distance measure for hidden return models. AT&T Technical Journal 62, 391–408 (1985)
Blass, A., Gurevich, Y., Nachmanson, L., Veanes, M.: Play to test. Technical report, Microsoft Research (2005)
Veanes, M., Roy, P., Campbell, C.: Online testing with reinforcement learning. In: Havelund, K., Núñez, M., Roşu, G., Wolff, B. (eds.) FATES 2006 and RV 2006. LNCS, vol. 4262, pp. 240–253. Springer, Heidelberg (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhioua, S., Precup, D., Laviolette, F., Desharnais, J. (2009). Learning the Difference between Partially Observable Dynamical Systems. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2009. Lecture Notes in Computer Science(), vol 5782. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04174-7_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-04174-7_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04173-0
Online ISBN: 978-3-642-04174-7
eBook Packages: Computer ScienceComputer Science (R0)