Optimal Policies for Status Update Generation in an IoT Device With Heterogeneous Traffic.
George StamatakisNikolaos PappasApostolos TraganitisPublished in: IEEE Internet Things J. (2020)
Keyphrases
- optimal policy
- markov decision processes
- decision problems
- state space
- finite horizon
- state dependent
- reinforcement learning
- finite state
- long run
- infinite horizon
- dynamic programming
- sufficient conditions
- average reward
- multistage
- average reward reinforcement learning
- dynamic programming algorithms
- serial inventory systems
- markov decision problems
- bayesian reinforcement learning
- initial state
- average cost
- control policies
- policy iteration
- semi markov decision processes