Optimal Transmission Policy Based on POMDP over Ka-Band Channels in SINs.
Xindong SuiJian JiaoShushi GuShaohua WuQinyu ZhangWeiqiang WuPublished in: CSPS (2017)
Keyphrases
- optimal policy
- markov decision process
- asymptotically optimal
- reinforcement learning
- model free reinforcement learning
- control policy
- state dependent
- dynamic programming
- optimal solution
- allocation policy
- finite horizon
- optimal control
- partially observable markov decision processes
- information fusion
- dynamical systems
- infinite horizon
- average reward
- continuous state
- policy evaluation
- partially observable
- expected cost
- state space
- fading channels
- optimal strategy
- point based value iteration
- finite state