Towards Risk-Averse Edge Computing With Deep Reinforcement Learning.

Dianlei Xu Xiang Su Huandong Wang Sasu Tarkoma Pan Hui

Published in: IEEE Trans. Mob. Comput. (2024)

Keyphrases

risk averse
reinforcement learning
risk neutral
utility function
decision makers
risk aversion
stochastic programming
function approximation
portfolio management
dynamic programming
optimal policy
multistage
markov decision processes
model free