Following Newton direction in Policy Gradient with parameter exploration.

Giorgio Manganini Matteo Pirotta Marcello Restelli Luca Bascetta

Published in: IJCNN (2015)

Keyphrases

policy gradient
parametric optimization
reinforcement learning
actor critic
gradient method
model free reinforcement learning
least squares
optimal control
function approximation
reinforcement learning algorithms
approximation methods
model selection
dynamic programming