Semi-infinite weighted Markov decision processes with perturbation.
Mohammed AbbadKhalid RahhaliPublished in: Math. Methods Oper. Res. (2004)
Keyphrases
- markov decision processes
- semi infinite
- linear program
- dynamic programming
- state space
- optimal policy
- optimality conditions
- transition matrices
- policy iteration
- semidefinite
- reinforcement learning
- average cost
- linear programming
- decision theoretic planning
- quadratic program
- finite dimensional
- infinite horizon
- average reward
- graphical models
- markov decision process
- supervised learning
- least squares
- feature space