arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.09295math.OC
收藏

可达性约束下MDP的最小化总折扣费用问题

On Minimizing Total Discounted Cost in MDPs Subject to Reachability Constraints

Yagiz Savas, Christos K. Verginis, Michael Hibbard, Ufuk Topcu

摘要:

我们研究的综合政策的马尔可夫决策过程(MDP)之后,一个代理达到目标状态的MDP,同时最小化其总的折扣成本。该问题结合了可达性标准与折扣成本标准,自然地表示完成任务的概率保证和最佳的瞬态性能。我们首先建立一个最佳的政策考虑制定可能不存在,但总是存在一个接近最佳的平稳策略。我们还提供了一个充要条件的最优策略的存在。然后,我们限制我们的注意力固定的确定性策略,并表明,与最佳固定的确定性策略的合成判定问题是NP-完全的。最后,我们提供了一个基于混合整数线性规划的精确算法,并提出了一个有效的近似算法的基础上线性规划的最佳静态确定性策略的合成。

英文摘要:

We study the synthesis of a policy in a Markov decision process (MDP) following which an agent reaches a target state in the MDP while minimizing its total discounted cost. The problem combines a reachability criterion with a discounted cost criterion and naturally expresses the completion of a task with probabilistic guarantees and optimal transient performance. We first establish that an optimal policy for the considered formulation may not exist but that there always exists a near-optimal stationary policy. We additionally provide a necessary and sufficient condition for the existence of an optimal policy. We then restrict our attention to stationary deterministic policies and show that the decision problem associated with the synthesis of an optimal stationary deterministic policy is NP-complete. Finally, we provide an exact algorithm based on mixed-integer linear programming and propose an efficient approximation algorithm based on linear programming for the synthesis of an optimal stationary deterministic policy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑