Finite State Markovian Decision Processes
Finite State Markovian Decision Processes
On some algorithms for limiting average Markov decision processes
Operations Research Letters
A decomposition algorithm for limiting average Markov decision problems
Operations Research Letters
| Hi-index | 0.00 |
It is shown that the communicating property of Markov Decision Processes (MDPs) is equivalent to satisfaction of sets of linear equations. A mapping between the 'multichain' and 'unichain' linear programs for undiscounted MDPs is developed by applying this equivalence. The mapping is used to prove that the simpler linear program solves communicating MDPs.