Login / Signup
A Markov Decision Process (MDP)-Based Congestion-Aware Medium Access Strategy for IEEE 802.15.4.
Bharat Shrestha
Ekram Hossain
Kae Won Choi
Sergio Camorlinga
Published in:
GLOBECOM (2011)
Keyphrases
</>
optimal policy
markov decision process
reward function
markov decision processes
inverse reinforcement learning
dynamic programming
state space
multimedia
reinforcement learning
data processing
real time
low cost
long run