Generalized Compatible Function Approximation for Policy Gradient Search.

Yiming Peng Gang Chen Mengjie Zhang Shaoning Pang

Published in: ICONIP (1) (2016)

Keyphrases

function approximation
policy gradient
reinforcement learning
actor critic
function approximators
learning tasks
temporal difference learning
search space
temporal difference
radial basis function
model free
reinforcement learning algorithms
support vector
artificial neural networks
optimal control