Benaim, M. (1995). Convergence theorems for hybrid learning rules. Neural Computation, 7(1):19--24. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
A Learning Rate Analysis of Reinforcement Learning Algorithms .. - Garcia, Ndiaye (1998) (Correct)
.... in the introduction of the averaged differential equation d dt = H( where H( lim n 1 E[H( Xn ) the behaviour of which can be compared to the asymptotic behaviour of (6) The use of the ODE method for analysing learning algorithms like neural nets has originally been introduced by Benaim [Benaim, 1995]. An application to the analysis of reinforcement learning algorithms has already been considered in [Bertsekas and Tsitsiklis, 1996, Kushner and Yin, 1997] where convergence analysis of Q Learning are presented. The point we want to emphasize in this article is that the ODE method can also be ....
Benaim, M. (1995). Convergence Theorem for Hybrid Learning Rules. Neural Computation, 7(1):19--25.
Hybrid Systems Architectures - Kurfeß (1996) (Correct)
No context found.
Benaim, M. (1995). Convergence theorems for hybrid learning rules. Neural Computation, 7(1):19--24.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC