Double Q-learning for Demand Response of an Electric Water Heater.

Thijs Peirelinck Chris Hermans Fred Spiessens Geert Deconinck

Published in: ISGT Europe (2019)

Keyphrases

reinforcement learning
cooperative
function approximation
state space
learning algorithm
multi agent
optimal policy
stochastic approximation
action selection
reinforcement learning algorithms
inventory control
power transmission
water supply
inventory systems
dynamic programming
multi agent systems
decision making