Certainty equivalent control of discrete time Markov processes with the average reward functional.
Lukasz StettnerPublished in: Syst. Control. Lett. (2023)
Keyphrases
- markov processes
- average reward
- markov chain
- markov process
- semi markov decision processes
- stochastic processes
- markov decision processes
- long run
- continuous time markov chains
- non stationary
- optimal policy
- random fields
- stochastic process
- finite state
- state space
- reinforcement learning
- markov model
- control strategy