Login / Signup
A robust control-theory-based exploration strategy in deep reinforcement learning for virtual network embedding.
Ghina Dandachi
Sophie Cerf
Yassine Hadjadj Aoul
Abdelkader Outtagarts
Éric Rutten
Published in:
Comput. Networks (2022)
Keyphrases
</>
control theory
reinforcement learning
exploration strategy
dynamical systems
state space
unknown environments
linear systems
function approximation
locally optimal
machine learning
learning algorithm
control law
genetic algorithm