Abstract
Relational reinforcement learning is presented, a learning technique that combines reinforcement learning with relational learning or inductive logic programming. Due to the use of a more expressive representation language to represent states, actions and Q-functions, relational reinforcement learning can be potentially applied to a new range of learning tasks. One such task that we investigate is planning in the block's world, where it is assumed that the effects of the actions are unknown to the agent and the agent has to learn a policy. Within this simple domain we show that relational reinforcement learning solves some existing problems with reinforcement learning. In particular, relational reinforcement learning allows to employ structural representations, to make abstraction of specific goals pursued and to exploit the results of previous learning phases when addressing new (more complex) situations.
This paper appears in the Proceedings of the Fifteenth International Conference on Machine Learning and is reprinted with permission.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Blockeel, H., and De Raedt, L. (1997) Experiments with Top-down Induction of Logical Decision Trees. Artificial Intelligence. Forthcoming.
Borrajo, D., and Veloso, M. (1997) Lazy incremental learning of control knowledge for efficiently obtaining quality plans. AI Review, 11(1-5): 371–405.
Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. (1984) Classification and Regression Trees. Wadsworth, Belmont.
Blockeel, H., and De Raedt, L. (1997) Lookahead and discretization in ILP. In Proc. 7th Intl. Workshop on Inductive Logic Programming, pages 77–84, Springer, Berlin.
Chapman, D., and Kaelbling, L. (1991) Input generalization in delayed reinforcement learning: An algorithm and performance comparisons. In Proc. 12th Intl. Joint Conf. on Artificial Intelligence, Morgan Kaufmann, San Mateo, CA.
De Raedt, L., and Blockeel, H. (1997) Using logical decision trees for clustering. In Proc. 7th Intl. Workshop on Inductive Logic Programming, pages 133–141, Springer, Berlin.
Fikes, R.E., and Nilsson, N.J. (1971) STRIPS: A new approach to the application of theorem proving. Artificial Intelligence, 2(3/4): 189–208.
Kaelbling, L., Littman, M., and Moore, A. (1996) Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4: 237–285.
Kramer, S. (1996) Structural regression trees. In Proc. 13th Natl. Conf. on Artificial Intelligence. AAAI Press, Menlo Park, CA.
Lavrač, N. and Džeroski, S. (1994) Inductive Logic Programming: Techniques and Applications. Ellis Horwood, Chichester.
Mitchell, T. (1997) Machine Learning. McGraw-Hill, New York.
Muggleton, S., and De Raedt, L. (1994) Inductive logic programming: Theory and methods. Journal of Logic Programming 19/20: 629–679.
Tesauro, G. (1995) Temporal difference learning and TD-GAMMON. Communications of the ACM, 38(3): 58–68.
Watkins, C., and Dayan, P. (1992) Q-learning. Machine Learning, 8: 279–292.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Džeroski, S., De Raedt, L., Blockeel, H. (1998). Relational reinforcement learning. In: Page, D. (eds) Inductive Logic Programming. ILP 1998. Lecture Notes in Computer Science, vol 1446. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0027307
Download citation
DOI: https://doi.org/10.1007/BFb0027307
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64738-6
Online ISBN: 978-3-540-69059-7
eBook Packages: Springer Book Archive