Optimal Cycling of a Heterogenous Battery Bank via Reinforcement Learning.

Vivek Deulkar Jayakrishnan Nair

Published in: SmartGridComm (2021)

Keyphrases

reinforcement learning
dynamic programming
optimal control
markov decision processes
optimal solution
evolutionary algorithm
worst case
function approximation
approximate dynamic programming
data mining
learning algorithm
learning process
upper bound
closed form
varying degrees
temporal difference learning