Applying Q-learning approach to CSMA Scheme to dynamically tune the contention probability.

Floriano De Rango Nicola Cordeschi Francesco Ritacco

Published in: CCNC (2021)

Keyphrases

learning algorithm
reinforcement learning
cooperative
multi agent
state space
classification scheme
neural network
reinforcement learning algorithms
temporal difference learning
dynamic programming
probability distribution
sensor networks
function approximation
model free
detection scheme
stochastic approximation