Login / Signup
A Policy Gradient with Parameter-Based Exploration Approach for Zone-Heating.
Kevin Van Vaerenbergh
Yann-Michaël De Hauwere
Bruno Depraetere
Kristof Van Moffaert
Ann Nowé
Published in:
SSCI (2015)
Keyphrases
</>
policy gradient
parametric optimization
gradient method
function approximation
optimal control
actor critic
reinforcement learning
model free reinforcement learning
reinforcement learning algorithms
approximation methods
learning tasks