An Actor-Critic Reinforcement Learning Approach for Energy Harvesting Communications Systems.

Ala'eddin Masadeh Zhengdao Wang Ahmed E. Kamal

Published in: ICCCN (2019)

Keyphrases

reinforcement learning
actor critic
temporal difference
reinforcement learning algorithms
linear programming
function approximation
policy gradient
state space
supervised learning
neural network
machine learning
objective function
optimal policy
action selection