A decomposition algorithm for limiting average Markov decision problems.
Mohammed AbbadHatim BoustiquePublished in: Oper. Res. Lett. (2003)
Keyphrases
- decomposition algorithm
- markov decision problems
- working set
- average cost
- decomposition method
- optimal policy
- state space
- linear programming
- partially observable
- reinforcement learning
- decision theoretic
- decision processes
- long run
- recognition algorithm
- dynamic programming
- expected utility
- queueing networks
- policy iteration
- markov decision processes
- neural network