On optimal policies for control and estimation over a Gaussian relay channel.
Ali A. ZaidiSerdar YükselTobias J. OechteringMikael SkoglundPublished in: CDC/ECC (2011)
Keyphrases
- optimal policy
- markov decision processes
- decision problems
- control policies
- finite horizon
- reinforcement learning
- state space
- dynamic programming
- infinite horizon
- average reward
- multistage
- average reward reinforcement learning
- dynamic programming algorithms
- control system
- finite state
- long run
- sufficient conditions
- initial state
- policy iteration
- bayesian reinforcement learning
- state dependent
- serial inventory systems
- markov decision process
- lost sales
- motion control
- average cost
- semi markov decision processes
- control strategies
- control strategy
- machine learning