Accelerated modified policy iteration algorithms for Markov decision processes

作者：Shlakhter Oleksandr^*; Lee Chi Guhn

来源：Mathematical Methods of Operations Research, 2013, 78(1): 61-76.

DOI：10.1007/s00186-013-0432-y

• Markov decision processes
• Policy iteration
• Modified policy iteration
• Accelerated convergence

We propose a new approach to accelerate the convergence of the modified policy iteration method for Markov decision processes with the total expected discounted reward. In the new policy iteration an additional operator is applied to the iterate generated by Markov operator, resulting in a bigger improvement in each iteration.

• 出版日期2013-8