scholarly journals ON THE IDENTIFICATION AND MITIGATION OF WEAKNESSES IN THE KNOWLEDGE GRADIENT POLICY FOR MULTI-ARMED BANDITS

2016 ◽  
Vol 31 (2) ◽  
pp. 239-263 ◽  
Author(s):  
James Edwards ◽  
Paul Fearnhead ◽  
Kevin Glazebrook
Keyword(s):  
Decision Making ◽  
Exponential Family ◽  
Numerical Study ◽  
Ranking And Selection ◽  
Gittins Index ◽  
Selection Problems ◽  
Index Policies ◽  
Online Decision Making ◽  
New Policies ◽  
Knowledge Gradient

The knowledge gradient (KG) policy was originally proposed for online ranking and selection problems but has recently been adapted for use in online decision-making in general and multi-armed bandit problems (MABs) in particular. We study its use in a class of exponential family MABs and identify weaknesses, including a propensity to take actions which are dominated with respect to both exploitation and exploration. We propose variants of KG which avoid such errors. These new policies include an index heuristic, which deploys a KG approach to develop an approximation to the Gittins index. A numerical study shows this policy to perform well over a range of MABs including those for which index policies are not optimal. While KG does not take dominated actions when bandits are Gaussian, it fails to be index consistent and appears not to enjoy a performance advantage over competitor policies when arms are correlated to compensate for its greater computational demands.

scholarly journals MCDM approach for weighted ranking of candidates in e-voting

2019 ◽  
Vol 86 ◽  
pp. 8-22 ◽  
Author(s):  
Rasim Alguliyev ◽  
Ramiz Aliguliyev ◽  
Farhad Yusifov
Keyword(s):  
Decision Making ◽  
Numerical Study ◽  
Ranking And Selection ◽  
Multi Criteria Decision Making ◽  
Linguistic Variables ◽  
Multi Criteria Evaluation ◽  
Qualified Personnel ◽  
Proposed Model ◽  
Decision Making Model ◽  
Selection Of

The aim of the study is the application of multi-criteria evaluation methods for ranking of candidates in e-voting. Due to the potential to enhance the electoral efficiency in e-voting multiple criteria, such as personality traits, activity and reputation in social media, opinion followers on election area and so on for the selection of qualified personnel can be considered. In this case, the number of criteria excesses in the decision-making stage directed us to the use of a multi-criteria decision making model (MCDM). This paper proposes MCDM for weighted ranking of candidates in e-voting. Criteria for the candidates’ ranking and selection are determined and each voter uses the linguistic scales for the ranking of each candidate. Candidates’ ranking is evaluated according to all criteria. In a numerical study, it is provided the candidates’ evaluation on the base of selected criteria and ranked according to the importance of criteria. To assess the importance of the criteria and to evaluate the suitability of the candidates for each of the criteria, the voters use linguistic variables. In practice, the proposed model can use different evaluation scales for the selection of candidates in e-voting. The proposed model allows selecting a candidate with the competencies based on the criteria set out in the e-voting process and making more effective decisions.

scholarly journals Evaluation of the Use of Shared Decision Making in Breast Cancer: International Survey

2021 ◽  
Vol 18 (4) ◽  
pp. 2128
Author(s):  
Marta Maes-Carballo ◽  
Manuel Martín-Díaz ◽  
Luciano Mignini ◽  
Khalid Saeed Khan ◽  
Rubén Trigueros ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Decision Making ◽  
Shared Decision Making ◽  
Health Professionals ◽  
Cross Sectional Study ◽  
Shared Decision ◽  
Online Questionnaire ◽  
Cross Sectional ◽  
Professional Societies ◽  
New Policies

Objectives: To assess shared decision-making (SDM) knowledge, attitude and application among health professionals involved in breast cancer (BC) treatment. Materials and Methods: A cross-sectional study based on an online questionnaire, sent by several professional societies to health professionals involved in BC management. There were 26 questions which combined demographic and professional data with some items measured on a Likert-type scale. Results: The participation (459/541; 84.84%) and completion (443/459; 96.51%) rates were high. Participants strongly agreed or agreed in 69.57% (16/23) of their responses. The majority stated that they knew of SDM (mean 4.43 (4.36–4.55)) and were in favour of its implementation (mean 4.58 (4.51–4.64)). They highlighted that SDM practice was not adequate due to lack of resources (3.46 (3.37–3.55)) and agreed on policies that improved its implementation (3.96 (3.88–4.04)). The main advantage of SDM for participants was patient satisfaction (38%), and the main disadvantage was the patients’ paucity of knowledge to understand their disease (24%). The main obstacle indicated was the lack of time and resources (40%). Conclusions: New policies must be designed for adequate training of professionals in integrating SDM in clinical practice, preparing them to use SDM with adequate resources and time provided.

scholarly journals Data-Driven Dispatching Rules Mining and Real-Time Decision-Making Methodology in Intelligent Manufacturing Shop Floor with Uncertainty

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4836
Author(s):  
Liping Zhang ◽  
Yifan Hu ◽  
Qiuhua Tang ◽  
Jie Li ◽  
Zhixiong Li
Keyword(s):  
Decision Making ◽  
Data Base ◽  
Real Time ◽  
Manufacturing Industry ◽  
Job Shop ◽  
Data Driven ◽  
Dispatching Rules ◽  
Shop Floor ◽  
Production Data ◽  
Online Decision Making

In modern manufacturing industry, the methods supporting real-time decision-making are the urgent requirement to response the uncertainty and complexity in intelligent production process. In this paper, a novel closed-loop scheduling framework is proposed to achieve real-time decision making by calling the appropriate data-driven dispatching rules at each rescheduling point. This framework contains four parts: offline training, online decision-making, data base and rules base. In the offline training part, the potential and appropriate dispatching rules with managers’ expectations are explored successfully by an improved gene expression program (IGEP) from the historical production data, not just the available or predictable information of the shop floor. In the online decision-making part, the intelligent shop floor will implement the scheduling scheme which is scheduled by the appropriate dispatching rules from rules base and store the production data into the data base. This approach is evaluated in a scenario of the intelligent job shop with random jobs arrival. Numerical experiments demonstrate that the proposed method outperformed the existing well-known single and combination dispatching rules or the discovered dispatching rules via metaheuristic algorithm in term of makespan, total flow time and tardiness.

scholarly journals Public Transportation Hub Location with Stochastic Demand: An Improved Approach Based on Multiple Attribute Group Decision-Making

2015 ◽  
Vol 2015 ◽  
pp. 1-15 ◽  
Author(s):  
Sen Liu ◽  
Zhilan Song ◽  
Shuqi Zhong
Keyword(s):  
Decision Making ◽  
Group Decision Making ◽  
Public Transportation ◽  
Group Decision ◽  
Numerical Study ◽  
Hub Location ◽  
Hub Location Problem ◽  
The Public ◽  
Multiple Attribute ◽  
Qualitative Factors

Urban public transportation hubs are the key nodes of the public transportation system. The location of such hubs is a combinatorial problem. Many factors can affect the decision-making of location, including both quantitative and qualitative factors; however, most current research focuses solely on either the quantitative or the qualitative factors. Little has been done to combine these two approaches. To fulfill this gap in the research, this paper proposes a novel approach to the public transportation hub location problem, which takes both quantitative and qualitative factors into account. In this paper, an improved multiple attribute group decision-making (MAGDM) method based on TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and deviation is proposed to convert the qualitative factors of each hub into quantitative evaluation values. A location model with stochastic passenger flows is then established based on the above evaluation values. Finally, stochastic programming theory is applied to solve the model and to determine the location result. A numerical study shows that this approach is applicable and effective.

scholarly journals The Role of Consumer Autonomy in Developing Sustainable AI: A Conceptual Framework

2021 ◽  
Vol 13 (4) ◽  
pp. 2332
Author(s):  
Lena Bjørlo ◽  
Øystein Moen ◽  
Mark Pasquine
Keyword(s):  
Decision Making ◽  
Decision Aids ◽  
Privacy Regulation ◽  
Advantages And Disadvantages ◽  
Fundamental Significance ◽  
Research Gap ◽  
Online Decision Making ◽  
Definition Of ◽  
Consumer Autonomy

Artificial intelligence (AI)-based decision aids are increasingly employed by businesses to assist consumers’ decision-making. Personalized content based on consumers’ data brings benefits for both consumers and businesses, i.e., with regards to more relevant content. However, this practice simultaneously enables increased possibilities for exerting hidden interference and manipulation on consumers, reducing consumer autonomy. We argue that due to this, consumer autonomy represents a resource at the risk of depletion and requiring protection, due to its fundamental significance for a democratic society. By balancing advantages and disadvantages of increased influence by AI, this paper addresses an important research gap and explores the essential challenges related to the use of AI for consumers’ decision-making and autonomy, grounded in extant literature. We offer a constructive, rather than optimistic or pessimistic, outlook on AI. Hereunder, we present propositions suggesting how these problems may be alleviated, and how consumer autonomy may be protected. These propositions constitute the fundament for a framework regarding the development of sustainable AI, in the context of online decision-making. We argue that notions of transparency, complementarity, and privacy regulation are vital for increasing consumer autonomy and promoting sustainable AI. Lastly, the paper offers a definition of sustainable AI within the contextual boundaries of online decision-making. Altogether, we position this paper as a contribution to the discussion of development towards a more socially sustainable and ethical use of AI.

On transforming an index for generalised bandit problems

1995 ◽  
Vol 32 (1) ◽  
pp. 168-182 ◽  
Author(s):  
K. D. Glazebrook ◽  
S. Greatrix
Keyword(s):  
Dynamic Programming ◽  
Policy Evaluation ◽  
Gittins Index ◽  
Bandit Problem ◽  
Bandit Problems ◽  
Index Policies

Nash (1980) demonstrated that index policies are optimal for a class of generalised bandit problem. A transform of the index concerned has many of the attributes of the Gittins index. The transformed index is positive-valued, with maximal values yielding optimal actions. It may be characterised as the value of a restart problem and is hence computable via dynamic programming methodologies. The transformed index can also be used in procedures for policy evaluation.

scholarly journals An Approach to the Extreme Miniaturization of Rotary Comb Drives

Actuators ◽  
2018 ◽  
Vol 7 (4) ◽  
pp. 70 ◽  
Author(s):  
Andrea Veroli ◽  
Alessio Buzzin ◽  
Fabrizio Frezza ◽  
Giampiero de Cesare ◽  
Muhammad Hamidullah ◽  
...  
Keyword(s):  
Decision Making ◽  
Compliant Mechanisms ◽  
Compliant Mechanism ◽  
Numerical Study ◽  
Information Gathering ◽  
Low Power Consumption ◽  
Sensors And Actuators ◽  
Comb Drive ◽  
Innovative Design ◽  
Comb Drives

The evolution of microelectronic technologies is giving constant impulse to advanced micro-scaled systems which perform complex operations. In fact, the actual micro and nano Electro-Mechanical Systems (MEMS/NEMS) easily integrate information-gathering and decision-making electronics together with all sorts of sensors and actuators. Mechanical manipulation can be obtained through microactuators, taking advantage of magnetostrictive, thermal, piezoelectric or electrostatic forces. Electrostatic actuation, more precisely the comb-drive approach, is often employed due to its high versatility and low power consumption. Moreover, the device design and fabrication process flow can be simplified by compliant mechanisms, avoiding complex elements and unorthodox materials. A nano-scaled rotary comb drive is herein introduced and obtained using NEMS technology, with an innovative design which takes advantages of the compliant mechanism characteristics. A theoretical and numerical study is also introduced to inspect the electro-mechanical behavior of the device and to describe a new technological procedure for its fabrication.

scholarly journals Coordinating a Supply Chain with a Loss-Averse Retailer and Effort Dependent Demand

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Liying Li ◽  
Yong Wang
Keyword(s):  
Decision Making ◽  
Supply Chain ◽  
Loss Aversion ◽  
Special Class ◽  
Numerical Study ◽  
Supply Chain Performance ◽  
Channel Coordination ◽  
Gain Loss ◽  
Decision Making Behavior ◽  
Dependent Demand

This study investigates the channel coordination issue of a supply chain with a risk-neutral manufacturer and a loss-averse retailer facing stochastic demand that is sensitive to sales effort. Under the loss-averse newsvendor setting, a distribution-free gain/loss-sharing-and-buyback (GLB) contract has been shown to be able to coordinate the supply chain. However, we find that a GLB contract remains ineffective in managing the supply chain when retailer sales efforts influence the demand. To effectively coordinate the channel, we propose to combine a GLB contract with sales rebate and penalty (SRP) contract. In addition, we discover a special class of gain/loss contracts that can coordinate the supply chain and arbitrarily allocate the expected supply chain profit between the manufacturer and the retailer. We then analyze the effect of loss aversion on the retailer’s decision-making behavior and supply chain performance. Finally, we perform a numerical study to illustrate the findings and gain additional insights.

Sign in / Sign up

Export Citation Format

Share Document