Optimal Policy Derivation for Transmission Duty-Cycle Constrained LPWAN.
Ruben Martinez-SandovalAntonio-Javier García-SánchezJoan García-HaroThomas M. ChenPublished in: IEEE Internet Things J. (2018)
Keyphrases
- optimal policy
- duty cycle
- markov decision processes
- decision problems
- reinforcement learning
- finite horizon
- dynamic programming
- real time
- state space
- infinite horizon
- long run
- state dependent
- multistage
- markov decision process
- lost sales
- bayesian reinforcement learning
- average reward
- average cost
- markov decision problems
- inventory level
- sufficient conditions
- control policies
- parallel algorithm
- serial inventory systems