Title :
New tests of optimality in Markov decision processes
Author :
Lasserre, Jean B.
Author_Institution :
Lab. d´´Autom. et d´´Anal. des Syst., CNRS, Toulouse, France
Abstract :
Presents some new results on detection of optimal and non-optimal actions in Markov decision processes. In the discounted case the author provides two new tests to eliminate non-optimal actions and to keep optimal actions. These two conditions are direct extensions of similar conditions in the average cost case. The author then derives a new MacQueen type test for action elimination in the average cost case
Keywords :
Markov processes; decision theory; minimisation; MacQueen type test; Markov decision processes; action elimination; average cost; discounted case; nonoptimal actions; optimal actions; optimality tests; Cost function; Ear; State-space methods; Testing;
Conference_Titel :
Decision and Control, 1994., Proceedings of the 33rd IEEE Conference on
Conference_Location :
Lake Buena Vista, FL
Print_ISBN :
0-7803-1968-0
DOI :
10.1109/CDC.1994.411025
