Least Squares Solutions of the HJB Equation With Neural Network Value-Function Approximators.

Yuval Tassa Tom Erez

Published in: IEEE Trans. Neural Networks (2007)

Keyphrases

least squares
neural network
function approximators
hamilton jacobi bellman
reinforcement learning
function approximation
control problems
optimal control
artificial neural networks
optimal solution
differential equations
nonlinear systems
temporal difference
action space