Neuro-Dynamic Programming
Learning Algorithms for Markov Decision Processes with Average Cost
SIAM Journal on Control and Optimization
Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)
Communication over fading channels with delay constraints
IEEE Transactions on Information Theory
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
This article briefly surveys a connected body work of the author and his collaborators on opportunistic transmission over a randomly varying channel. Both single user and multi-user scenarios are considered and a reinforcement learning based scheme proposed for both, with provable convergence properties.