Quickest change detection approach to optimal control in Markov decision processes with model changes.
Taposh BanerjeeMiao LiuJonathan P. HowPublished in: ACC (2017)
Keyphrases
- change detection
- markov decision processes
- optimal control
- risk sensitive
- reinforcement learning
- dynamic programming
- state space
- image registration
- sufficient conditions
- infinite horizon
- finite state
- neural network
- policy iteration
- markov decision process
- average cost
- optimal policy
- linear program
- decision theoretic
- remote sensing
- objective function
- machine learning
- real time
- gamma distributions