Optimal risk probability for first passage models in semi-Markov decision processes

This paper studies the risk minimization problem in semi-Markov decision processes with denumerable states. The criterion to be optimized is the risk probability (or risk function) that a first passage time to some target set doesn't exceed a threshold value. We first characterize such risk functions and the corresponding optimal value function, and prove that the optimal value function satisfies the optimality equation by using a successive approximation technique. Then, we present some properties of optimal policies, and further give conditions for the existence of optimal policies. In addition, a value iteration algorithm and a policy improvement method for obtaining respectively the optimal value function and optimal policies are developed. Finally, two examples are given to illustrate the value iteration procedure and essential characterization of the risk function.     

Qualitative operators for reasoning maps: Evaluating multi-criteria options with networks of reasons

Cognitive/causal maps have been widely used as a powerful way of capturing decision-makers’ views about a problem, representing it as a cause–effect discourse. Several ways of making causal inferences from this type of model have been proposed in the Operational Research and Artificial Intelligence literatures, but none, as far as we are aware, has attempted to use a causal map structure to perform a multi-criteria evaluation of decision alternatives. Recently, we have proposed a new multi-criteria method, denominated as a Reasoning Map, which permits the use of decision-makers’ reasoning, structured as a network of means-and-ends (a particular type of causal map) to perform such an evaluation. In this manner, the model resembles the way that people talk and think about decisions in practice. The method also pays explicit attention to the cognitive limitations of decision-makers in providing preference information. Thus it employs qualitative assessment of preferences, utilises aggregation operators for qualitative data and provides also qualitative outputs. In this paper we discuss and evaluate possible ways of aggregating qualitative performance information in Reasoning Maps.     

A multi-parametric programming approach for multilevel hierarchical and decentralised optimisation problems

In this paper, we outline the foundations of a general global optimisation strategy for the solution of multilevel hierarchical and general decentralised multilevel problems, based on our recent developments on multi-parametric programming and control theory. The core idea is to recast each optimisation subproblem, present in the hierarchy, as a multi-parametric programming problem, with parameters being the optimisation variables belonging to the remaining subproblems. This then transforms the multilevel problem into single-level linear/convex optimisation problems. For decentralised systems, where more than one optimisation problem is present at each level of the hierarchy, Nash equilibrium is considered. A three person dynamic optimisation problem is presented to illustrate the mathematical developments.     

A Bayesian approach to seafloor classification using multi-beam echo-sounder backscatter data

Seafloor classification using acoustic remote sensing techniques is an attractive approach due to its high-coverage capabilities and limited costs. The multi-beam echo-sounder (MBES) system provides high-resolution bathymetry and backscatter information with 100% coverage. In this paper, we present a seafloor classification method that employs the MBES backscatter data. The method uses the averaged backscatter data per beam. It, therefore, is independent on the quality of the MBES calibration. Also, its performance is insensitive to seafloor type variation along the MBES swathe and corrections for the angular dependence of the backscatter are not needed. The method accounts for the ping-to-ping variability of the backscatter intensity. It estimates both the number of seafloor types present in the survey area and the probability density function for the backscatter strength at a certain angle for each of the seafloor types. Application of the method to MBES backscatter data acquired in a well-known test area in the North Sea shows very good agreement with available ground truth. The method’s discriminatory performance for this area is demonstrated to be comparable to that of taking samples of the sediment. All seafloor types known to be present in the area are resolved for. Application of the method to the Stanton bank data set shows clearly separable areas that differ in seafloor composition.     

Analysis of multiobjective decision problems by the indifference band approach

A new approach, based on indifference band, for analyzing problems with multiple objectives is described. The relations of this approach to some previous results are given. Methods for generating nondominated solutions are supplied.     

A note on asymptotic inference in a class of non-stationary processes

In this note some problems of asymptotic inference in a class of non-stationary stochastic processes are considered. In particular, it is shown that no criterion based on the existence of uniformly most powerful tests over a local neighborhood can be used in this situation.     

瓶罐玻璃行业企业绩效评价

笔者依据所能获得的资料———《瓶罐玻璃行业企业经济信息汇编》[6],建立了一套经济实用的瓶罐玻璃行业企业绩效评价指标体系;提供了一种科学评价方法和计算机化的评价技术;能适时地对该行业内各企业绩效进行评价和比较分析;及时获得各企业在全行业内竞争位次;及时发现影响企业绩效的主要因素;为高层管理者制定和调整企业管理决策提供了参考依据。     

One-armed bandit models with continuous and delayed responses

One-armed bandit processes with continuous delayed responses are formulated as controlled stochastic processes following the Bayesian approach. It is shown that under some regularity conditions, a Gittins-like index exists which is the limit of a monotonic sequence of break-even values characterizing optimal initial selections of arms for finite horizon bandit processes. Furthermore, there is an optimal stopping solution when all observations on the unknown arm are complete. Results are illustrated with a bandit model having exponentially distributed responses, in which case the controlled stochastic process becomes a Markov decision process, the Gittins-like index is the Gittins index and the Gittins index strategy is optimal. Acknowledgement.We thank an anonymous referee for constructive and insightful comments, especially those related to the notion of the Gittins index.Both authors are funded by the Natural Sciences and Engineering Research Council (NSERC) of Canada.     

从极优基未必能迅达最优基：兼与文献[1]作者商榷

本对献[1]提出的“求解线性规划的快速换基迭代法”从多阶段决策的观点阐述并举证了从极优基未必能快速到达最优基的论断。旨在说明用此方法求解一般线性规划问题时不一定能实现快速换基迭代的概念。     

基于最小错误率贝叶斯决策的企业员工招聘决策

本在[1]和[2]研究基础上，利用[1]、[2]中的分析模型和综合评价模型所得的结果。以及这两个结果正相关性。依据某大型国有企管理初级岗位3000多人的测试结果。采用最小错误率贝叶斯决策。构建了企业管理岗位初级人员招聘模型。此模型为企业根据企业化和价值观等来招聘符合企业要求的员工提供了一种方法。