Answers are grounded in this paper and cite their sources.
The method of successive approximations for solving problems on single-chain Markovian decision processes has been investigated by White and Schweitzer. This paper shows that White's scheme not only converges, but also can be modified so that monotonic upper and lower bounds on the maximal gain can be obtained.
No takes yet. Share an insight, caveat, or question.
Amedeo R. Odoni (1969) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: