Advertisement

Machine Learning

, Volume 15, Issue 3, pp 299–319 | Cite as

Associative reinforcement learning: A generate and test algorithm

  • Leslie Pack Kaelbling
Article

Abstract

An agent that must learn to act in the world by trial and error faces thereinforcement learning problem, which is quite different from standard concept learning. Although good algorithms exist for this problem in the general case, they are often quite inefficient and do not exhibit generalization. One strategy is to find restricted classes of action policies that can be learned more efficiently. This paper pursues that strategy by developing an algorithm that performans an on-line search through the space of action mappings, expressed as Boolean formulae. The algorithm is compared with existing methods in empirical trials and is shown to have very good performance.

Keywords

reinforcement learning generalization generate-and-test 

References

  1. Duda, R. O., Gaschnig, J., & Hart, P. E. (1979). Model design in the Prospector consultant system for mineral exploration. In D. Michie (Ed.),Expert Systems in the Micro Electronic Age. Edinburgh, U.K.: Edinburgh University Press.Google Scholar
  2. Duda, R. O., Hart, P. E., & Nilsson, N. J. (1976).Subjective Bayesian Methods for Rule-Based Inference Systems. Technical Report 124. Artificial Intelligence Center, SRI International, Menlo Park, California.Google Scholar
  3. Kaelbling, L. P. (1994). Associative reinforcement learning: Functions ink-DNF.Machine Learning, 15, 279–298.Google Scholar
  4. Kaelbling, L. P. (1993).Learning in Embedded Systems. Cambridge, Massachusetts: The MIT Press. Also available as a PhD Thesis from Stanford University, 1990.Google Scholar
  5. Saxena, S. (1991).Predicting the Effect of Instance Representations on Inductive Learning. PhD thesis, University of Massachusetts, Amherst, Massachusetts.Google Scholar
  6. Schlimmer, J. C. (1987).Concept Acquisition Through Representational Adjustment. PhD thesis, University of California, Irvine, Irvine, California.Google Scholar
  7. Schlimmer, J. C. & Granger, Jr., R. H. (1986). Incremental learning from noisy data.Machine Learning, 1(3), 317–354.Google Scholar

Copyright information

© Kluwer Academic Publishers 1994

Authors and Affiliations

  • Leslie Pack Kaelbling
    • 1
  1. 1.Computer Science DepartmentBrown UniversityProvidenceUSA

Personalised recommendations