Average optimal stationary policies: convexity and convergence conditions in linear stochastic control systems.
Alessandro N. VargasJoão Bosco Ribeiro do ValPublished in: CDC (2009)
Keyphrases
- stationary policies
- markov decision processes
- average cost
- state space
- sufficient conditions
- dynamic programming
- markov decision process
- linear program
- finite state
- lot sizing
- action sets
- optimal policy
- control system
- long run
- infinite horizon
- markov decision problems
- optimal control
- reinforcement learning
- multistage
- initial state
- finite number
- reward function
- markov chain
- state dependent
- optimal solution
- model checking
- monte carlo
- partially observable
- inventory level
- least squares
- np hard