NUMERICAL ENCLOSURE FOR THE OPTIMAL THRESHOLD PROBABILITY IN DISCOUNTED MARKOV DECISION PROCESSES
スポンサーリンク
概要
- 論文の詳細を見る
There are various procedures to compute the optimal threshold probability in discounted Markov decision processes. In the actual numerical computation of an approximate optimal solution, the estimation of the discrepancy between the approximate solution and the exact solution is important. White(1993 b) derived such an error estimation for the value iteration method, however, this estimation is not actually in the computable form. In this paper, we present a numerical enclosure method to compute the optimal threshold probability, that guarantees a rigorous a posteriori error bound.
- Research Association of Statistical Sciencesの論文
Research Association of Statistical Sciences | 論文
- CLUSTERING BY A FUZZY METRIC : APPLICATIONS TO THE CLUSTER-MEDIAN PROBLEM
- A FAMILY OF REGRESSION MODELS HAVING PARTIALLY ADDITIVE AND MULTIPLICATIVE COVARIATE STRUCTURE
- AN OPTIMAL STOPPING PROBLEM ON TREE
- ON THE ORDERS OF MAX-MIN FUNCTIONALS
- TREE EXPRESSIONS AND THEIR PRODUCT FORMULA