Bounds for the Finite Horizon Cost of Markov Jump Linear Systems with Additive Noise and Convergence for the Long Run Average Cost.
Alessandro N. VargasEduardo F. CostaJoão B. R. do ValPublished in: CDC (2006)
Keyphrases
- finite horizon
- additive noise
- linear systems
- long run average cost
- optimal policy
- lot size
- sufficient conditions
- infinite horizon
- average cost
- markov chain
- markov decision processes
- noisy images
- spatial domain
- state space
- random variables
- dynamical systems
- maximum likelihood
- decision problems
- finite state
- long run
- markov decision process
- reinforcement learning
- dynamic programming
- lower bound
- multistage
- state dependent
- machine learning
- optimal control
- inventory level
- asymptotically optimal
- speech signal
- pid controller
- stochastic process
- total cost
- initial state
- expected cost
- lot sizing
- lead time
- image denoising
- bayesian networks