Analysis of temporal-difference learning with function approximation

Advances in Neural Information Processing Systems

Volumn , Issue , 1997, Pages 1075-1081

  Tsitsiklis, John N ^a   Van Roy, Benjamin ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION ERRORS; FINITE STATE; FUNCTION APPROXIMATION; FUNCTION APPROXIMATORS; LINEAR FUNCTIONS; PARAMETER VECTORS; PARAMETERIZED; TEMPORAL DIFFERENCE LEARNING;

MARKOV PROCESSES;

EID: 84887003012     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Baird, L. C. (1995). "Residual Algorithms: Reinforcement Learning with Function Approximation," in Prieditis & Russell, eds. Machine Learning: Proceedings of the Twelfth International Conference, 9-12 July, Morgan Kaufman Publishers, San Francisco, CA.
2. Bertsekas, D. P. (1994) "A Counter-Example to Temporal-Difference Learning," Neural Computation, vol. 7, pp. 270-279.
3. Bertsekas, D. P. (1995) Dynamic Programming and Optimal Control, Athena Scientific, Belmont, MA.
4. Bertsekas, D. P. h Tsitsiklis, J. N. (1996) Neuro-Dynamic Programming, Athena Scientific, Belmont, MA.
5. Benveniste, A., Metivier, M., & Priouret, P., (1990) Adaptive Algorithms and Stochastic Approximations, Springer-Verlag, Berlin.
6. Dayan, P. D. & Singh, S. P (1996) "Mean Squared Error Curves in Temporal Difference Learning," preprint.
7. Gurvits, L. (1996) personal communication.
8. Sutton, R. S., (1988) "Learning to Predict by the Method of Temporal Differences," Machine Learning, vol. 3, pp. 9-44.
9. Sutton, R.S. (1995) "On the Virtues of Linear Learning and Trajectory Distributions," Proceedings of the Workshop on Value Function Approximation, Machine Learning Conference 1995, Boyan, Moore, and Sutton, Eds., p. 85. Technical Report CMU-CS-95-206, Carnegie Mellon University, Pittsburgh, PA 15213.
10. Tsitsiklis, J. N. & Van Roy, B. (1996) "An Analysis of Temporal-Difference Learning with Function Approximation," to appear in the IEEE Transactions on Automatic Control.