Abstract
Multi-modal control is a commonly used design tool for breaking up complex control tasks into sequences of simpler tasks. In this paper, we show that by viewing the control space as a set of such tokenized instructions rather than as real-valued signals, reinforcement learning becomes applicable to continuous-time control systems. In fact, we show how a combination of state-space exploration and multi-modal control converts the original system into a finite state machine, on which Q-learning can be utilized.
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
Bhatia, A., Frazzoli, E.: Incremental Search Methods for Reachability Analysis of Continuous and Hybrid Systems. In: Hybrid Systems: Computation and Control. Springer, Heidelberg (2004)
Bicchi, A., Marigo, A., Piccoli, B.: On the reachability of quantized control systems. IEEE Transactions on Automatic Control 4(47), 546–563 (2002)
Bicchi, A., Marigo, A., Piccoli, B.: Encoding steering control with symbols. In: IEEE International Conference on Decision and Control, pp. 3343–3348 (2003)
Bradtke, S.J., Ydstie, B.E., Barto, A.G.: Adaptive linear quadratic control using policy iteration. In: American Control Conference, pp. 3475–3479 (1994)
Crawford, L., Sastry, S.S.: Learning Controllers for Complex Behavioral Systems. In: Neural Information Processing Systems Tenth Annual Conference (NIPS 1996) (1996)
Egerstedt, M.: On the Specification Complexity of Linguistic Control Procedures. International Journal of Hybrid Systems 2(1-2), 129–140 (2002)
Egerstedt, M., Hristu-Varsakelis, D.: Observability and Policy Optimization for Mobile Robots. In: IEEE Conference on Decision and Control, Las Vegas, NV (December 2002)
Egerstedt, M., Brockett, R.W.: Feedback Can Reduce the Specification Complexity of Motor Programs. IEEE Transactions on Automatic Control 48(2), 213–223 (2003)
Jaakkola, T., Jordan, M.I., Singh, S.P.: On the Convergence of stochastic iterative dynamic programming algorithms. Neural Computation 6(6) (1994)
Kaebling, L.P., Littman, M.L., Cassandra, A.R.: Learning Policies for Partially Observable Environments: Scaling Up. In: Proceedings of the Twelfth International Conference on Machine Learning (1995)
Kaebling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal Of Artificial Intelligence Research (1996)
Morgansen, K., Brockett, R.W.: Optimal Regulation and Reinforcement Learning for the Nonholonomic Integrator. In: Proceedings of the American Control Conference, June 2000, pp. 462–466 (2000)
Sutton, R.S.: Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding. Neural Information Processing Systems 8 (1996)
Sutton, R.S., Barto, A.G.: Reinforcement Learning, An Introduction. MIT Press, Cambridge (1998)
Tabuada, P., Pappas, G.: Model Checking LTL over Controllable Linear Systems is Decidable. In: Hybrid Systems: Computation and Control. Springer, Prague (2003)
Tsitsiklis, J.N.: Asynchronous stochastic approximation and Q-learning. Machine Learning 16(3) (1994)
Watkins, C.J.C.H., Dayan, P.: Q-learning. Machine Learning 8(3/4), 257–277 (1992)
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
Mehta, T.R., Egerstedt, M. (2005). Learning Multi-modal Control Programs. In: Morari, M., Thiele, L. (eds) Hybrid Systems: Computation and Control. HSCC 2005. Lecture Notes in Computer Science, vol 3414. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-31954-2_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-31954-2_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25108-8
Online ISBN: 978-3-540-31954-2
eBook Packages: Computer ScienceComputer Science (R0)