Linear Approximation based Q-Learning for Edge Caching in Massive MIMO Networks.
Navneet GargMathini SellathuraiTharmalingam RatnarajahPublished in: ACSSC (2019)
Keyphrases
- linear approximation
- policy iteration
- reinforcement learning
- basis functions
- state action
- cooperative
- learning algorithm
- state space
- model free
- markov decision processes
- function approximation
- dynamic programming
- linear programming
- evaluation function
- reinforcement learning algorithms
- least squares
- optimal policy
- fixed point