Two ε-Optimal Nonlinear Reinforcement Schemes for Stochastic Automata.

Yoshikazu Sawaragi Norio Baba

Published in: IEEE Trans. Syst. Man Cybern. (1974)

Keyphrases

approximation schemes
optimal solution
cellular automata
monte carlo
reinforcement learning
piecewise linear
neural network
state dependent
locally optimal
nonlinear equations
linear quadratic