Optimal threshold probability in undiscounted Markov decision processes with a target set
書誌事項
- 公開日
- 2004-02
- 権利情報
-
- https://www.elsevier.com/tdm/userlicense/1.0/
- DOI
-
- 10.1016/s0096-3003(03)00158-9
- 公開者
- Elsevier BV
この論文をさがす
説明
We consider risk minimizing problems in undiscounted Markov decisions processes with a target set. We formulate the problem as an infinite horizon case with a recurrent class. We show that an optimal value function is a unique solution to an optimality equation and there exists an stationary optimal policy. Also we give several value iteration methods and a policy improvement method.
収録刊行物
-
- Applied Mathematics and Computation
-
Applied Mathematics and Computation 149 (2), 519-532, 2004-02
Elsevier BV