Blocking- and Delay-aware Flow Control Using Markov Decision Process.

Yixuan Wang Changyin Sun Fan Jiang Jing Jiang

Published in: ICCC (2020)

Keyphrases

flow control
markov decision process
optimal policy
state dependent
state space
markov decision processes
low bandwidth
reinforcement learning
infinite horizon
initial state
dynamic programming
search algorithm
sufficient conditions
wireless networks
reward function
high bandwidth