This paper presents a maintenance policy for a system consisting of two units. Unit 1 is gradually deteriorating and is subject to soft failure. Unit 2 has a general lifetime distribution and is subject to hard failure. Condition of unit 1 of the system is monitored periodically and it is considered as failed when its deterioration level reaches or exceeds a critical level N . At the failure ti...

In this paper we consider a two-stage ordering problem with a buyer’s minimum commitment quantity contract. Under the contract the buyer is required to give a minimum-commitment quantity. Then the manufacturer has the obligations to supply the minimum-commitment quantity and to provide a shortage compensation policy to the buyer. We formulate a dynamic optimization model to determine the manufa...

Due to the impact of time-dependent unit unavailability, the testing strategies (e.g., simultaneous or staggered testing) have significant effect on the system unavailability for complex standby systems. Several testing strategies have been studied to minimize average system unavailability for certain systems. For example, uniformly staggered testing has been shown to be the best for two identi...

We study an M/M/2 queueing system with two heterogeneous servers under a variant vacation policy, where the two servers may take together at most J vacations when the system is empty. A quasi-birth-and-death process is formulated to analyze the system. We obtain the explicit expressions of the stationary distribution of the system size and the mean system size. We also show that the number of v...

In this paper, we propose to use deep policy networks which are trained with an advantage actor-critic method for statistically optimised dialogue systems. First, we show that, on summary state and action spaces, deep Reinforcement Learning (RL) outperforms Gaussian Processes methods. Summary state and action spaces lead to good performance but require pre-engineering effort, RL knowledge, and ...

Given any allocation of parliament seats among parties, we characterize all the stable government configurations (supported by at least a majority of the parliament) in terms of winning coalitions and policy outcomes. We consider a two dimensional policy space and we assume that there are four parties that care mainly about holding office, and only instrumentally about policy. We find that for ...

A two-level rejuvenation policy for software systems with degradation process is studied. Both full restarts and partial restarts are considered in this rejuvenation strategy. A semi-Markov process model is constructed, and based on its closed-form solution we obtain the system availability as a bivariate function. Then, the rejuvenation policy is analyzed to maximize the system availability. S...

In this paper, a discount model is proposed to coordinate pricing and ordering decisions in a two-echelon supply chain (SC). Demand is stochastic and price sensitive while lead times are fixed. Decentralized decision making where downstream decides on selling price and order size is investigated. Then, joint pricing and ordering decisions are extracted where both members act as a single entity ...