A note on policy algorithms for discounted Markov decision problems

作者：Ng, MK^*

来源：Operations Research Letters, 1999, 25(4): 195-197.

DOI：10.1016/S0167-6377(99)00051-6

• discounted Markov decision process
• policy algorithm
• matrices

In this note, we show that the evaluation phase in the policy iteration algorithm for the infinite horizon discounted Markov decision problem can be done in O(mN(2)) operations, where N is the number of states of the Markov decision process and m is the number of states in which the decision changes during the policy improvement phase.

• 出版日期1999-11
• 单位香港大学