Abstract
In this paper we introduce negation into Logical Markov Decision Processes, which is a model of Relational Reinforcement Learning. In the new model nLMDP the abstract state space can be constructed in a simple way, so that a good property of complementarity holds. Prototype action is also introduced into the model. A distinct feature of the model is that applicable abstract actions can be obtained automatically with valid substitutions. Given a complementary abstract state space and a set of prototype actions, a model-free Θ-learing method is implemented for evaluating the state-action-substitution value funcion.
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
Kaelbling, L., Littman, M., Moore, A.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research 4, 237–285 (1996)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Džeroski, S., De Raedt, L., Driessens, K.: Relational reinforcement learning. Machine Learning 43, 7–52 (2001)
Driessens, K., Ramon, J.: Relational instrance based regression for relational reinforcement learning. In: ICML 2003 (2003)
Gärtner, T., Driessens, K., Ramon, J.: Graph kernels and gaussian processes for relational reinforcement learning. In: Horváth, T., Yamamoto, A. (eds.) ILP 2003. LNCS, vol. 2835, pp. 146–163. Springer, Heidelberg (2003)
Cole, J., Lloyd, K., Ng, K.: Symbolic learning for adaptive agents. In: The Annual Partner Conference, Smart Internet Technology Cooperative Research Centre (2003)
Yoon, S., Fern, A., Givan, R.: Inductive policy selection for first-order MDPs. In: UAI 2002 (2002)
Fern, A., Yoon, S., Givan, R.: Approximate policy iteration with a policy language bias. In: NIPS 2003 (2003)
Boutilier, C., Reiter, R., Price, B.: Symbolic dynamic programming for first-order MDPs. In: Seventeenth International Joint Conference on Artificial Intelligence (IJCAI 2001), pp. 690–700 (2001)
Kersting, K., De Raedt, L.: Logical markov decision programs. In: IJCAI 2003 Workshop on Learning Statistical Models of Relational Data (2003)
Van Otterlo, M.: Reinforcement learning for relational MDPs. In: Machine Learning Conference of Belgium and the Netherlands (BeNeLearn 2004) (2004)
Morales, E.: Scaling up reinforcement learning with a relational representation. In: Proceedings of the Workshop on Adaptability in Multi-agent Systems at AORC 2003, Sydney (2003)
Guestrin, C., Koller, D., Gearhart, C., Kanodia, N.: Generalizing plans to new environments in relational MDPs. In: IJCAI 2003 (2003)
Kersting, K., De Raedt, L.: Logical markov decision programs and the convergence of logical TD(λ). In: Camacho, R., King, R., Srinivasan, A. (eds.) ILP 2004. LNCS, vol. 3194, pp. 180–197. Springer, Heidelberg (2004)
Nienhuys-Cheng, S.-H., de Wolf, R.: Foundations of Inductive Logic Programming. Lecture Notes in Artifical Intelligence, vol. 1228. Springer, Heidelberg (1997)
Clark, K.L.: Negation as failure. In: Logic and Data Bases, pp. 293–322 (1977)
Van Otterlo, M., Kersting, K.: Challenges for relational reinforcement learning. In: ICML 2004 Workshop on Relational Reinforcement Learning (2004)
Slaney, J., Thiébaux, S.: Blocks world revisited. Artificial Intelligence 125, 119–153 (2001)
Kersting, K., Van Otterlo, M., De Raedt, L.: Bellman goes relational. In: ICML 2004 (2004)
Lecoeuche, R.: Learning optimal dialogue management rules by using reinforcement learning and inductive logic programming. In: Proc. of the North American Chapter of the Association for Computational Linguistics (NAACL) (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhiwei, S., Xiaoping, C. (2006). Unique State and Automatical Action Abstracting Based on Logical MDPs with Negation. In: Jiao, L., Wang, L., Gao, X., Liu, J., Wu, F. (eds) Advances in Natural Computation. ICNC 2006. Lecture Notes in Computer Science, vol 4222. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11881223_118
Download citation
DOI: https://doi.org/10.1007/11881223_118
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-45907-1
Online ISBN: 978-3-540-45909-5
eBook Packages: Computer ScienceComputer Science (R0)