On the worst-case analysis of temporal-difference learning algorithms

Machine Learning

Volumn 22, Issue 1-3, 1996, Pages 95-121

  Schapire, Robert E ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

Machine learning; On line learning; Temporal difference learning; Worst case analysis

Indexed keywords

EID: 0013419177     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1007/BF00114725     Document Type: Article

References (8)

1. Nicolo Cesa-Bianchi, Philip M. Long, & Manfred K. Warmuth. (1993). Worst-case quadratic loss bounds for a generalization of the Widrow Hoff rule. In Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, pages 429-438.
2. Peter Dayan (1992). The convergence of TD(λ) for general λ. Machine Learning, 8(3/4):341-362.
3. Peter Dayan & Terrence J. Sejnowski (1994) TD(λ) converges with probability I. Machine Learning, 14(3):295-301.
4. Roger A Horn & Charles R. Johnson (1985) Matrix Analysis Cambridge University Press.
5. Tommi Jaakkola, Michael I. Jordan. & Satinder P. Singh. (1993). On the convergence of stochastic iterative dynamic programming algorithms Technical Report 9307, MIT Computational Cognitive Science.
6. Jyrki Kivinen & Manfred K. Warmuth (1994) Additive versus exponentiated gradient updates for learning linear functions Technical Report UCSC-CRL-94-16, University of California Santa Cruz, Computer Research Laboratory.
7. Richard S. Sutton. (1988). Learning to predict by the methods of temporal differences Machine Learning, 3:9-44.
8. C. J. C. H. Watkins (1989) Learning from delayed rewards PhD thesis, University of Cambridge, England, 1989.