Illustrated review of convergence conditions of the value iteration algorithm and the rolling horizon procedure for average-cost MDPs.
Eugenio Della VecchiaSilvia Di MarcoAlain Jean-MariePublished in: Ann. Oper. Res. (2012)
Keyphrases
- markov decision processes
- dynamic programming
- average cost
- cost function
- policy iteration
- convergence rate
- infinite horizon
- stochastic shortest path
- optimal solution
- computational complexity
- search space
- probabilistic model
- linear programming
- learning algorithm
- objective function
- long run
- finite state
- np hard
- markov decision chains
- iterative algorithms
- markov decision process
- heuristic search
- optimal policy
- sufficient conditions