Abstract
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the environment of the learning agent can be considered as stationary, generalized policy iteration frameworks, because of the interleaving of learning and control, will produce non-stationarity of the evaluated policy and so of its value function. Tracking the optimal solution instead of trying to converge to it is therefore preferable. In this paper, we propose to handle this tracking issue with a Kalman-based temporal difference framework. Complexity and convergence analysis are studied. Empirical investigations of its ability to handle non-stationarity is finally provided.
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
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1996)
Phua, C.W., Fitch, R.: Tracking Value Function Dynamics to Improve Reinforcement Learning with Piecewise Linear Function Approximation. In: International Conference on Machine Learning, ICML 2007 (2007)
Sutton, R.S., Koop, A., Silver, D.: On the role of tracking in stationary environments. In: Proceedings of the 24th international conference on Machine learning, pp. 871–878 (2007)
Geist, M., Pietquin, O., Fricout, G.: Kalman Temporal Differences: the deterministic case. In: Proceedings of the IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2009), Nashville, TN, USA (April 2009)
Kalman, R.E.: A New Approach to Linear Filtering and Prediction Problems. Transactions of the ASME–Journal of Basic Engineering 82(Series D), 35–45 (1960)
Julier, S.J., Uhlmann, J.K.: Unscented filtering and nonlinear estimation. Proceedings of the IEEE 92(3), 401–422 (2004)
van der Merwe, R.: Sigma-Point Kalman Filters for Probabilistic Inference in Dynamic State-Space Models. PhD thesis, Oregon Health&Science University, Portland, USA (2004)
Bradtke, S.J., Barto, A.G.: Linear Least-Squares Algorithms for Temporal Difference Learning. Machine Learning 22(1-3), 33–57 (1996)
Baird, L.C.: Residual Algorithms: Reinforcement Learning with Function Approximation. In: Proceedings of the International Conference on Machine Learning, pp. 30–37 (1995)
Antos, A., Szepesvári, C., Munos, R.: Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path. Machine Learning 71(1), 89–129 (2008)
Kakade, S.: A natural policy gradient. In: Advances in Neural Information Processing Systems 14 (NIPS 2001), Vancouver, British Columbia, Canada, pp. 1531–1538 (2001)
Peters, J., Vijayakumar, S., Schaal, S.: Natural actor-critic. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 280–291. Springer, Heidelberg (2005)
Boyan, J.A.: Technical Update: Least-Squares Temporal Difference Learning. Machine Learning 49(2-3), 233–246 (1999)
Lagoudakis, M.G., Parr, R.: Least-Squares Policy Iteration. Journal of Machine Learning Research 4, 1107–1149 (2003)
Jo, S., Kim, S.W.: Consistent Normalized Least Mean Square Filtering with Noisy Data Matrix. IEEE Transactions on Signal Processing 53(6), 2112–2123 (2005)
Engel, Y., Mannor, S., Meir, R.: Reinforcement Learning with Gaussian Processes. In: Proceedings of Internation Conference on Machine Learning, ICML 2005 (2005)
Bhatnagar, S., Sutton, R.S., Ghavamzadeh, M., Lee, M.: Incremental Natural Actor-Critic Algorithms. In: Advances in Neural Information Processing Systems, Vancouver, vol. 21 (2008)
Geist, M., Pietquin, O., Fricout, G.: Bayesian Reward Filtering. In: Girgin, S., Loth, M., Munos, R., Preux, P., Ryabko, D. (eds.) EWRL 2008. LNCS (LNAI), vol. 5323, pp. 96–109. Springer, Heidelberg (2008)
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
Geist, M., Pietquin, O., Fricout, G. (2009). Tracking in Reinforcement Learning. In: Leung, C.S., Lee, M., Chan, J.H. (eds) Neural Information Processing. ICONIP 2009. Lecture Notes in Computer Science, vol 5863. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10677-4_57
Download citation
DOI: https://doi.org/10.1007/978-3-642-10677-4_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10676-7
Online ISBN: 978-3-642-10677-4
eBook Packages: Computer ScienceComputer Science (R0)