Robust optimal strategies in Markov decision problems
نویسندگان
چکیده
An optimal strategy in a Markov decision problem is robust if it is optimal in every decision problem (not necessarily stationary) that is close to the original problem. We prove that when the state and action spaces are finite, an optimal strategy is robust if and only if it is the unique optimal strategy.
منابع مشابه
What is Decidable about Partially Observable Markov Decision Processes with ω-Regular Objectives
We consider partially observable Markov decision processes (POMDPs) with ω-regular conditions specified as parity objectives. The class of ω-regular languages extends regular languages to infinite strings and provides a robust specification language to express all properties used in verification, and parity objectives are canonical forms to express ω-regular conditions. The qualitative analysis...
متن کاملWhat is Decidable about Partially Observable Markov Decision Processes with omega-Regular Objectives
We consider partially observable Markov decision processes (POMDPs) with ω-regular conditions specified as parity objectives. The class of ω-regular languages extends regular languages to infinite strings and provides a robust specification language to express all properties used in verification, and parity objectives are canonical forms to express ω-regular conditions. The qualitative analysis...
متن کاملComputing Near Optimal Strategies for Stochastic Investment Planning Problems
We present efficient techniques for computing near optimal strategies for a class of stochastic commodity trading problems modeled as Markov decision processes (MDPs). The process has a continuous state space and a large action space and cannot be solved efficiently by standard dynamic programming methods. We exploit structural properties of the process, and combine it with MonteCarlo estimatio...
متن کاملA POMDP Framework to Find Optimal Inspection and Maintenance Policies via Availability and Profit Maximization for Manufacturing Systems
Maintenance can be the factor of either increasing or decreasing system's availability, so it is valuable work to evaluate a maintenance policy from cost and availability point of view, simultaneously and according to decision maker's priorities. This study proposes a Partially Observable Markov Decision Process (POMDP) framework for a partially observable and stochastically deteriorating syste...
متن کاملDetermining Optimal Stationary Strategies for Discounted Stochastic Optimal Control Problem on Networks
The stochastic version of discrete optimal control problem with infinite time horizon and discounted integral-time cost criterion is considered. This problem is formulated and studied on certain networks. A polynomial time algorithm for determining the optimal stationary strategies for the considered problems is proposed and some applications of the algorithm for related Markov decision problem...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Oper. Res. Lett.
دوره 42 شماره
صفحات -
تاریخ انتشار 2014