Autonomous PEV Charging Scheduling Using Dyna-Q Reinforcement Learning.

Fan Wang Jie Gao Mushu Li Lian Zhao

Published in: IEEE Trans. Veh. Technol. (2020)

Keyphrases

reinforcement learning
function approximation
temporal difference learning
autonomous learning
function approximators
earth observing
temporal difference
resource utilization
scheduling problem
scheduling algorithm

rl algorithms
reinforcement learning methods
state space
reinforcement learning algorithms
markov decision processes
resource allocation
learning capabilities
machine learning
resource constraints
cooperative

optimal policy
flexible manufacturing systems
electric vehicles
round robin
autonomous systems
policy search
fixed point
control problems
learning tasks

model free
optimal control
dynamic programming
evaluation function
np hard
transfer learning
radial basis function
action selection
robotic control