Abstract
Knowledge representation is an important issue in reinforcement learning. Although logic programming with answer set semantics is a standard in knowledge representation, it has not been exploited in reinforcement learning to resolve its knowledge representation issues. In this paper, we present a logic programming framework to reinforcement learning, by integrating reinforcement learning, in MDP environments, with normal hybrid probabilistic logic programs with probabilistic answer set semantics [29], that is capable of representing domain-specific knowledge. We show that any reinforcement learning problem, MT, can be translated into a normal hybrid probabilistic logic program whose probabilistic answer sets correspond to trajectories in MT. We formally prove the correctness of our approach. Moreover, we show that the complexity of finding a policy for a reinforcement learning problem in our approach is NP-complete. In addition, we show that any reinforcement learning problem, MT, can be encoded as a classical logic program with answer set semantics, whose answer sets corresponds to valid trajectories in MT. We also show that a reinforcement learning problem can be encoded as a SAT problem. In addition, we present a new high level action description language that allows the factored representation of MDP.
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
Baral, C., Tran, N., Tuan, L.C.: Reasoning about actions in a probabilistic setting. In: AAAI (2002)
Bagnell, J., Kakade, S., Ng, A., Schneider, J.: Policy search by dynamic programming. Neural Information Processing Systems 16 (2003)
Boutilier, C., Dean, T., Hanks, S.: Decision-theoretic planning: structural assumptions and computational leverage. Journal of AI Research 11, 1–94 (1999)
Boutilier, C., Reiter, R., Price, B.: Symbolic dynamic programming for first-order MDPs. In: 17th IJCAI (2001)
Dekhtyar, A., Subrahmanian, V.S.: Hybrid probabilistic program. Journal of Logic Programming 43(3), 187–250 (2000)
Eiter, T., Lukasiewicz, T.: Probabilistic reasoning about actions in nonmonotonic causal theories. In: 19th Conference on Uncertainty in Artificial Intelligence (2003)
Eiter, T., et al.: Declarative problem solving in dlv. In: Logic Based Artificial Intelligence (2000)
Gelfond, M., Lifschitz, V.: The stable model semantics for logic programming. In: ICSLP. MIT Press, Cambridge (1988)
Gelfond, M., Lifschitz, V.: Classical negation in logic programs and disjunctive databases. New Generation Computing 9(3-4), 363–385 (1991)
Gelfond, M., Lifschitz, V.: Representing action and change by logic programs. Journal of Logic Programming 17, 301–321 (1993)
Iocchi, L., Lukasiewicz, T., Nardi, D., Rosati, R.: Reasoning about actions with sensing under qualitative and probabilistic uncertainty. In: 16th European Conference on Artificial Intelligence (2004)
Kaelbling, L., Littman, M., Cassandra, A.: Planning and acting in partially observable stochastic domains. Artificial Intelligence 101, 99–134 (1998)
Kaelbling, L., Littman, M., Moore, A.: Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research 4, 237–285 (1996)
Kautz, H., Selman, B.: Pushing the envelope: planning, propositional logic, and stochastic search. In: 13th National Conference on Artificial Intelligence (1996)
Kersting, K., De Raedt, L.: Logical Markov decision programs and the convergence of logical TD(λ). In: 14th International Conference on Inductive Logic Programming (2004)
Kushmerick, N., Hanks, S., Weld, D.: An algorithm for probabilistic planning. Artificial Intelligence 76(1-2), 239–286 (1995)
Lifschitz, V.: Answer set planning. In: ICLP (1999)
Lin, F., Zhao, Y.: ASSAT: Computing answer sets of a logic program by SAT solvers. Artificial Intelligence 157(1-2), 115–137 (2004)
Majercik, S., Littman, M.: MAXPLAN: A new approach to probabilistic planning. In: 4th International Conference on Artificial Intelligence Planning, pp. 86–93 (1998)
Majercik, S., Littman, M.: Contingent planning under uncertainty via stochastic satisfiability. Artificial Intelligence 147(1–2), 119–162 (2003)
Mundhenk, M., Goldsmith, J., Lusena, C., Allender, E.: Complexity of finite-horizon Markov decision process problems. Journal of the ACM (2000)
Niemela, I., Simons, P.: Efficient implementation of the well-founded and stable model semantics. In: Joint International Conference and Symposium on Logic Programming, pp. 289–303 (1996)
Saad, E.: Incomplete knowlege in hybrid probabilistic logic programs. In: 10th European Conference on Logics in Artificial Intelligence (2006)
Saad, E.: Towards the computation of the stable probabilistic model semantics. In: 29th Annual German Conference on Artificial Intelligence (June 2006)
Saad, E.: A logical approach to qualitative and quantitative reasoning. In: 9th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (2007)
Saad, E.: Probabilistic planning in hybrid probabilistic logic programs. In: 1st International Conference on Scalable Uncertainty Management (2007)
Saad, E.: On the relationship between hybrid probabilistic logic programs and stochastic satisfiability. In: 10th International Symposium on Artificial Intelligence and Mathematics (2008)
Saad, E., Pontelli, E.: Towards a more practical hybrid probabilistic logic programming framework. In: Practical Aspects of Declarative Languages (2005)
Saad, E., Pontelli, E.: A new approach to hybrid probabilistic logic programs. Annals of Mathematics and Artificial Intelligence Journal 48(3-4), 187–243 (2006)
Son, T., Baral, C., Nam, T., McIlraith, S.: Domain-dependent knowledge in answer set planning. ACM Transactions on Computational Logic 7(4), 613–657 (2006)
Subrahmanian, V.S., Zaniolo, C.: Relating stable models and AI planning domains. In: International Conference of Logic Programming, pp. 233–247 (1995)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Saad, E. (2008). A Logical Framework to Reinforcement Learning Using Hybrid Probabilistic Logic Programs. In: Greco, S., Lukasiewicz, T. (eds) Scalable Uncertainty Management. SUM 2008. Lecture Notes in Computer Science(), vol 5291. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87993-0_27
Download citation
DOI: https://doi.org/10.1007/978-3-540-87993-0_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87992-3
Online ISBN: 978-3-540-87993-0
eBook Packages: Computer ScienceComputer Science (R0)