Abstract
Agents in reinforcement learning tasks may learn slowly in large or complex tasks — transfer learning is one technique to speed up learning by providing an informative prior. How to best enable transfer between tasks with different state representations and/or actions is currently an open question. This paper introduces the concept of a common task subspace, which is used to autonomously learn how two tasks are related. Experiments in two different nonlinear domains empirically show that a learned inter-state mapping can successfully be used by fitted value iteration, to (1) improving the performance of a policy learned with a fixed number of samples, and (2) reducing the time required to converge to a (near-) optimal policy with unlimited samples.
Keywords
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
Atkeson, C.G., Moore, A.W., Schaal, S.: Locally weighted learning. A.I. Rev. 11(1-5), 11–73 (1997)
Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems, pp. 81–93. IEEE Press (1990)
Busoniu, L., Babuska, R., De Schutter, B., Ernst, D.: Reinforcement Learning and Dynamic Programming Using Function Approximators, 1st edn. CRC Press, Inc., Boca Raton (2010)
Close, C.M., Fredrick, D.K., Newel, J.C.: Modeling and Analysis of Dynamic Systems, 3rd edn. John Wiley & Sons, Inc., Third Avenue (2002)
Konidaris, G., Barto, A.: Autonomous shaping: Knowledge transfer in reinforcement learning. In: ICML (2006)
Kuhlmann, G., Stone, P.: Graph-Based Domain Mapping for Transfer Learning in General Games. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladenič, D., Skowron, A. (eds.) ECML 2007. LNCS (LNAI), vol. 4701, pp. 188–200. Springer, Heidelberg (2007)
Liu, Y., Stone, P.: Value-function-based transfer for reinforcement learning using structure mapping. In: AAAI (July 2006)
Soni, V., Singh, S.: Using homomorphisms to transfer options across continuous reinforcement learning domains. In: AAAI (July 2006)
Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. IEEE Transactions on Neural Networks 9(5), 1054–1054 (1998)
Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: A survey. Journal of Machine Learning Research 10, 1633–1685 (2009)
Taylor, M.E., Stone, P., Liu, Y.: Transfer learning via inter-task mappings for temporal difference learning. J. of Machine Learning Research 8(1), 2125–2167 (2007)
Taylor, M.E., Jong, N.K., Stone, P.: Transferring Instances for Model-Based Reinforcement Learning. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008, Part II. LNCS (LNAI), vol. 5212, pp. 488–505. Springer, Heidelberg (2008)
Torrey, L., Walker, T., Shavlik, J., Maclin, R.: Using Advice to Transfer Knowledge Acquired in One Reinforcement Learning Task to Another. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 412–424. Springer, Heidelberg (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ammar, H.B., Taylor, M.E. (2012). Reinforcement Learning Transfer via Common Subspaces. In: Vrancx, P., Knudson, M., Grześ, M. (eds) Adaptive and Learning Agents. ALA 2011. Lecture Notes in Computer Science(), vol 7113. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-28499-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-28499-1_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-28498-4
Online ISBN: 978-3-642-28499-1
eBook Packages: Computer ScienceComputer Science (R0)