Splitting in a finite Markov decision problem.
Eric V. DenardoEugene A. FeinbergUriel G. RothblumPublished in: SIGMETRICS Perform. Evaluation Rev. (2012)
Keyphrases
- markov decision problems
- state and action spaces
- linear programming
- state space
- partially observable
- decision theoretic
- reinforcement learning
- markov decision processes
- optimal policy
- decision processes
- infinite horizon
- expected utility
- queueing networks
- finite number
- dynamic programming
- transition probabilities
- average cost
- action space
- utility function
- decision problems
- multi agent