Policy iteration vs Q-Sarsa approach optimization for embedded system communications with energy harvesting.
Mohammed AssaouyOuadoudi ZytouneDriss AboutajdinePublished in: ATSIP (2017)
Keyphrases
- policy iteration
- markov decision processes
- fixed point
- model free
- reinforcement learning
- sample path
- least squares
- optimal policy
- temporal difference
- markov decision process
- temporal difference learning
- finite state
- infinite horizon
- optimization algorithm
- average reward
- linear programming
- reinforcement learning algorithms
- function approximation
- convergence rate
- optimal control
- state space
- policy evaluation
- learning algorithm
- action space
- dynamic programming
- objective function
- image segmentation