The Art and Theory of Dynamic Programming von Dreyfus

Volltext

Totally model-free reinforcement learning by actor-critic Elman networks in non-Markovian domains von Mizutani, E., Dreyfus, S.E.

Volltext

On complexity analysis of supervised MLP-learning for algorithmic comparisons von Mizutani, E., Dreyfus, S.E.

Volltext

Stagewise Newton, differential dynamic programming, and neighboring optimum control for neural-network learning von Mizutani, E., Dreyfus, S.E.

Volltext

MLP's hidden-node saturations and insensitivity to initial weights in two classification benchmark problems: parity and two-spirals von Mizutani, E., Dreyfus, S.E.

Volltext

Second-order backpropagation algorithms for a stagewise-partitioned separable Hessian matrix von Mizutani, E., Dreyfus, S.E., Demmel, J.W.

Volltext

On derivation of MLP backpropagation from the Kelley-Bryson optimal-control gradient formula and its application von Mizutani, E., Dreyfus, S.E., Nishio, K.

Volltext

On using discretized Cohen-Grossberg node dynamics for model-free actor-critic neural learning in non-Markovian domains von Mizutani, E., Dreyfus, S.E.

Volltext bestellen

APPLICATION OF DYNAMIC PROGRAMMING TO THE AIRPLANE MINIMUM TIME-TO-CLIMB PROBLEM von CARTAINO,T.F, DREYFUS,S.E

Volltext bestellen