Two Simple Model-free Extremum Seeking Strategies with Convergence Acceleration through Hessian Estimation.

Laurent Dewasme Alain Vande Wouwer

Published in: CDC (2022)

Keyphrases

model free
reinforcement learning
reinforcement learning algorithms
neural network
function approximation
convergence speed
machine learning
genetic algorithm
learning tasks
convergence rate
training data
least squares
markov random field
transfer learning
step size
policy iteration