On optimal policies for control and estimation over a Gaussian relay channel.
Ali A. ZaidiSerdar YükselTobias J. OechteringMikael SkoglundPublished in: Autom. (2013)
Keyphrases
- optimal policy
- markov decision processes
- decision problems
- control policies
- reinforcement learning
- dynamic programming
- finite horizon
- multistage
- state space
- finite state
- long run
- infinite horizon
- state dependent
- optimal control
- dynamic programming algorithms
- average reward reinforcement learning
- policy iteration
- serial inventory systems
- initial state
- control strategies
- control strategy
- sufficient conditions
- control system
- partially observable markov decision processes
- average cost
- semi markov decision processes