Markov Decision Process Based Pilot Pattern Optimization for 5G V2X Communications.

Yan Yang Shuping Dang Yejun He Mohsen Guizani

Published in: GLOBECOM (2018)

Keyphrases

markov decision process
state space
markov decision processes
reinforcement learning
optimal policy
finite horizon
infinite horizon
temporal difference learning
partial observability
transition matrices
policy iteration
dynamic programming
learning algorithm
social networks
markov chain
finite state