Abstract
This paper demonstrates the exploitation of certain vision processing techniques to index into a case base of surfaces. The surfaces are the result of reinforcement learning and represent the optimum choice of actions to achieve some goal from anywhere in the state space. This paper shows how strong features that occur in the interaction of the system with its environment can be detected early in the learning process. Such features allow the system to identify when an identical, or very similar, task has been solved previously and to retrieve the relevant surface. This results in an orders of magnitude increase in learning rate.
Preview
Unable to display preview. Download preview PDF.
References
Agnar Aamodt and Enric Plaza (1994) Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches. AlCom — Artificial Intelligence Communications V. 7 No. 1 pp 39–37
Aha, D. W., and Salzberg, S. L. (1993). Learning to catch: Applying nearest neighbor algorithms to dynamic control tasks. Proc. Fourth International Workshop on Artificial Intelligence and Statistics, pp 363–368
C. H. Chin and C. R. Dyer (1986) Model-based recognition in Robot Vision. Computing surveys V. 18 No 1 pp 67–108
Kristian J. Hammond (1990) Case-Based Planning: A Framework for Planning from Experience. The Journal of Cognitive Science V. 14 no. 3
Jean-Yves Herve and Rajeev Sharma And Peter Cucka (1991) The Geometry of Visual Coordination. Proc. Ninth National Conf. on Artificial Intelligence pp 732–737
Frederic Leymarie and Martin D. Levine. (1993) Tracking Deformable Objects in the Plane Using an Active Contour Model. IEEE Trans. Pattern Analysis And Machine Intelligence V. 15 No. 6 pp 617–634
R. A. McCallum, (1995). Instance-based utile distinctions for reinforcement learning. Proc. Twelfth International Conf. on Machine Learning, pp 387–395
R. A. McCallum (1995). Instance-based state identification for reinforcement learning. Advances in Neural Information Processing Systems 7. pp 377–384
Staphane Mallat and Sifen Zhong (1992). Characterization of Signals from Multi-scale Edges. IEEE Trans. Pattern Analysis And Machine Intelligence V. 14 No. 7 pp 710–732
David Marr (1982) Vision: a computational investigation into the human repre-sentation and processing of visual information. W.H. Freeman
A. W. Moore and C. G. Atkeson (1993) Prioritized Sweeping: Reinforcement Learning with Less Data and Less Real Time. Machine Learning, V. 13 pp 103–130
Jing Peng (1995) Efficient Memory-Based Dynamic Programming. Proc. Twelfth International Conf. of Machine Learning pp 438–446
John W. Sheppard and Steven L. Salzberg (1996) A teaching strategy for memory-based control. To appear in AI Review, special issue on Lazy Learning.
P. Suetens and P. Fua and A. Hanson (1992) Computational strategies for object recognition. Computing surveys V. 24 No. 1 pp 5–61
R.S. Sutton (1988) Learning to Predict by the Methods of Temporal Differences. Machine Learning V. 3 pp 9–44
R.S. Sutton (1990) Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. Proc. Seventh International Conf. on Machine Learning pp 216–224
P. Tadepalli and D. Ok (1996) Scaling up Average Reward Reinforcement Learning by Approximating the Domain Models and the Value Function. Proc. Thirteenth International Conf. of Machine Learning pp 471–479
Manuela M. Veloso and Jaime G. Carbonell (1993) Derivational Analogy in PRODIGY: Automating Case Acquisition, storage and Utilization. Machine Learning V. 10 No. 3 pp 249–278
Christopher J.C.H. Watkins and Peter Dayan (1992) Technical Note:Q-learning Machine Learning V. 8 No 3–4 pp 279–292
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Drummond, C. (1997). Using a case base of surfaces to speed-up reinforcement learning. In: Leake, D.B., Plaza, E. (eds) Case-Based Reasoning Research and Development. ICCBR 1997. Lecture Notes in Computer Science, vol 1266. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63233-6_513
Download citation
DOI: https://doi.org/10.1007/3-540-63233-6_513
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63233-7
Online ISBN: 978-3-540-69238-6
eBook Packages: Springer Book Archive