Mean-Field Theory for Batched TD(λ)

Neural Computation

Volumn 9, Issue 7, 1997, Pages 1403-1419

  Pineda, Fernando J ^a  

^a JOHNS HOPKINS UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0003276733     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1997.9.7.1403     Document Type: Article

References (17)

1. Benveniste, A., Métivier, M., & Priouret, P. (1990). Adaptive Algorithms and Stochastic Approximations. Berlin: Springer-Verlag.
2. Bertsekas, D. P., & Tsitsiklis, J. N. (1996). Neuro-dynamic programming. Belmont, MA: Athena Scientific.
3. Dayan, P. (1992). The convergence of TD(λ) for general lambda. Machine Learning, 8, 341-362.
4. Dayan, P., & Sejnowski, T. J. (1994). TD(λ) converges with probability 1. Machine Learning, 14, 295-301.
5. Golub, G. H., & Van Loan, C. F. (1996). Matrix computations (3rd ed.). Baltimore: Johns Hopkins University Press.
6. Gordon G. J. (1996). Stable fitted reinforcement learning. In G. Tesauro, D. Touretzky, & T. Lean (Eds.), Advances in Neural Information Processing Systems: Proceedings of the 1996 Conference (pp. 1052-1058). Cambridge, MA: MIT Press.
7. Jaakkola, T., Jordan, M. I., & Singh, S. P. (1994). On the convergence of stochastic iterative dynamic programming algorithms. Neural Computation, 6, 1185-1201.
8. Kushner, H. J., & Clark, D. S. (1978). Stochastic approximation methods for constrained and unconstrained systems. New York: Springer-Verlag.
9. Pineda, F. J. (1995, August 23-26). Generalization in TD(λ). Theoretical Physics Institute, University of Minnesota.
10. Singh, S. P., & Dayan, P. (1996). Analytical mean squared error curves in temporal difference learning. In M. Mozer, M. Jordan, & T. Petsche (Eds.), Advances in Neural Information Processing Systems, 9. Cambridge, MA: MIT Press.
11. Singh, S. P., Jaakkola, T., & Jordan, M. (1995). Reinforcement learning with soft state aggregation. In G. Tesauro, D. Touretzky, & T. Lean (Eds.), Advances in Neural Information Processing Systems: Proceedings of the 1995 Conference (pp. 361-368). Cambridge, MA: MIT Press.
12. Sutton, R. S. (1988). Learning to predict by the methods of temporal differences. Machine Learning, 3, 9-44.
13. Tesauro, G. (1992). Practial issues in temporal difference learning. Machine Learning, 8, 257-277.
14. Tesauro, G. (1995). Temporal difference learning and TD-Gammon. Communications of the ACM, 38, 58-68.
15. Tsitsiklis, J. N. (1994). Asynchronous stochastic approximation and Q-learning. Machine Learning, 16, 185-202.
16. Tsitsiklis, J. N., & Van Roy, B. (1996a). Feature-based methods for large scale dynamic programming. Machine Learning, 22, 59-94.
17. Tsitsiklis, J. N., & Van Roy, B. (1996b). An analysis of temporal-difference learning with function approximation. (Tech. Rep. No. LIDS-P-2322). Cambridge, MA: MIT Laboratory for Information and Decision Systems.