A Reinforcement Learning Look at Risk-Sensitive Linear Quadratic Gaussian Control.

Leilei Cui Tamer Basar Zhong-Ping Jiang

Published in: L4DC (2023)

Keyphrases

optimal control
linear quadratic
risk sensitive
reinforcement learning
dynamic programming
control strategy
infinite horizon
real time
average cost
neural network
transfer learning
function approximation
temporal difference