Platform Behavior under Market Shocks: A Simulation Framework and Reinforcement-Learning Based Study

We study the behavior of an economic platform (e.g., Amazon, Uber Eats, Instacart) under shocks, such as COVID-19 lockdowns, and the effect of different regulation considerations. To this end, we develop a multi-agent simulation environment of a platform economy in a multi-period setting where shocks may occur and disrupt the economy. Buyers and sellers are heterogeneous and modeled as economically-motivated agents, choosing whether or not to pay fees to access the platform. We use deep reinforcement learning to model the fee-setting and matching behavior of the platform, and consider two major types of regulation frameworks: (1) taxation policies and (2) platform fee restrictions. We offer a number of simulated experiments that cover different market settings and shed light on regulatory tradeoffs. Our results show that while many interventions are ineffective with a sophisticated platform actor, we identify a particular kind of regulation - fixing fees to the optimal, no-shock fees while still allowing a platform to choose how to match buyers and sellers - as holding promise for promoting the efficiency and resilience of the economic system. © 2023 ACM.

How COVID-19 is Accelerating the Digital Revolution: Challenges and Opportunities

This book explores how digital technologies have proved to be a useful and necessary tool to help ensure that local and regional governments on the frontline of the emergency can continue to provide essential public services during the COVID-19 crisis. Indeed, as the demand for digital technologies grows, local and regional governments are increasingly committed to improving the lives of their citizens under the principles of privacy, freedom of expression and democracy. The Digital Revolution began between the late 1950s and 1970s and represents the evolution of technology from the mechanical and analog to the digital. The advent of digital technology has also changed how humans communicate today using computers, smartphones and the internet. Further, the digital revolution has made a tremendous wealth of information accessible to virtually everyone. In turn, the book focuses on key challenges for local and regional governments concerning digital technologies during this crisis, e.g. the balance between privacy and security, the digital divide, and accessibility. Privacy is a challenge in the mitigation of COVID-19, as governments rely on digital technologies like contact-tracking apps and big data to help trace peoples patterns and movements. While these methods are controversial and may infringe on rights to privacy, they also appear to be effective measures for rapidly controlling and limiting the spread of the virus. Next, the book discusses the 10 technology trends that can help build a resilient society, as well as their effects on how we do business, how we work, how we produce goods, how we learn, how we seek medical services and how we entertain ourselves. Lastly, the book addresses a range of diversified technologies, e.g. Online Shopping and Robot Deliveries, Digital and Contactless Payments, Remote Work, Distance Learning, Telehealth, Online Entertainment, Supply Chain 4.0, 3D Printing, Robotics and Drones, 5G, and Information and Communications Technology (ICT). © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Dynamic distributed decision-making for resilient resource reallocation in disrupted manufacturing systems

The COVID-19 pandemic brings many unexpected disruptions, such as frequently shifting markets and limited human workforce, to manufacturers. To stay competitive, flexible and real-time manufacturing decision-making strategies are needed to deal with such highly dynamic manufacturing environments. One essential problem is dynamic resource allocation to complete production tasks, especially when a resource disruption (e.g. machine breakdown) occurs. Though multi-agent methods have been proposed to solve the problem in a flexible and agile manner, the agent internal decision-making process and resource uncertainties have rarely been studied. This work introduces a model-based resource agent (RA) architecture that enables effective agent coordination and dynamic agent decision-making. Based on the RA architecture, a rescheduling strategy that incorporates risk assessment via a clustering agent coordination strategy is also proposed. A simulation-based case study is implemented to demonstrate dynamic rescheduling using the proposed multi-agent framework. The results show that the proposed method reduces the computational efforts while losing some throughput optimality compared to the centralised method. Furthermore, the case study illustrates that incorporating risk assessment into rescheduling decision-making improves the throughput. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

Supply Chain Network Model using Multi-Agent Reinforcement Learning for COVID-19

The COVID-19 vaccination management in Japan has revealed many problems. The number of vaccines available was clearly less than the number of people who wanted to be vaccinated. Initially, the system was managed by making reservations with age group utilizing vaccination coupons. After the second round of vaccinations, only appointments for vaccination dates were coordinated and vaccination sites were set up in Shibuya Ward where the vaccine could be taken freely. Under a shortage of vaccine supply, the inability to make appointments arose from a failure to properly estimate demand. In addition, the vaccine expired due to inadequate inventory management, resulting in the vaccine being discarded. This is considered to be a supply chain problem in which appropriate supply could not be provided in response to demand. In response to this problem, this paper examines whether it is possible to avoid shortage and stock discards by a decentralized management system for easy on-site inventory control instead of a centralized management system in real world. Based on a multi-agent model, a model was created to redistribute inventory to clients by predicting future shortage based on demand fluctuations and past inventory levels. The model was constructed by adopting the Kanto region. The validation results of the model showed that the number of discards was reduced by about 70% and out-of-stocks by about 12% as a result of learning the dispersion management and out-of-stock forecasting © 2023, International Journal of Advanced Computer Science and Applications.All Rights Reserved.

Hierarchical Multi-agent Model for Reinforced Medical Resource Allocation with Imperfect Information

With the advent of the COVID-19 pandemic, the shortage in medical resources became increasingly more evident. Therefore, efficient strategies for medical resource allocation are urgently needed. However, conventional rule-based methods employed by public health experts have limited capability in dealing with the complex and dynamic pandemic-spreading situation. In addition, model-based optimization methods such as dynamic programming (DP) fail to work since we cannot obtain a precise model in real-world situations most of the time. Model-free reinforcement learning (RL) is a powerful tool for decision-making;however, three key challenges exist in solving this problem via RL: (1) complex situations and countless choices for decision-making in the real world;(2) imperfect information due to the latency of pandemic spreading;and (3) limitations on conducting experiments in the real world since we cannot set up pandemic outbreaks arbitrarily. In this article, we propose a hierarchical RL framework with several specially designed components. We design a decomposed action space with a corresponding training algorithm to deal with the countless choices, ensuring efficient and real-time strategies. We design a recurrent neural network-based framework to utilize the imperfect information obtained from the environment. We also design a multi-agent voting method, which modifies the decision-making process considering the randomness during model training and, thus, improves the performance. We build a pandemic-spreading simulator based on real-world data, serving as the experimental platform. We then conduct extensive experiments. The results show that our method outperforms all baselines, which reduces infections and deaths by 14.25% on average without the multi-agent voting method and up to 15.44% with it. © 2022 Association for Computing Machinery.

Identifying Correlates of Emergent Behaviors in Agent-Based Simulation Models Using Inverse Reinforcement Learning

In large agent-based models, it is difficult to identify the correlate system-level dynamics with individual-level attributes. In this paper, we use inverse reinforcement learning to estimate compact representations of behaviors in large-scale pandemic simulations in the form of reward functions. We illustrate the capacity and performance of these representations identifying agent-level attributes that correlate with the emerging dynamics of large-scale multi-agent systems. Our experiments use BESSIE, an ABM for COVID-like epidemic processes, where agents make sequential decisions (e.g., use PPE/refrain from activities) based on observations (e.g., number of mask wearing people) collected when visiting locations to conduct their activities. The IRL-based reformulations of simulation outputs perform significantly better in classification of agent-level attributes than direct classification of decision trajectories and are thus more capable of determining agent-level attributes with definitive role in the collective behavior of the system. We anticipate that this IRL-based approach is broadly applicable to general ABMs. © 2022 IEEE.

School's Out? Simulating Schooling Strategies During COVID-19

Multi-agent based systems offer the possibility to examine the effects of policies down to specific target groups while also considering the effects on a population-level scale. To examine the impact of different schooling strategies, an agent-based model is used in the context of the COVID-19 pandemic using a German city as an example. The simulation experiments show that reducing the class size by rotating weekly between in-person classes and online schooling is effective at preventing infections while driving up the detection rate among children through testing during weeks of in-person attendance. While open schools lead to higher infection rates, a surprising result of this study is that school rotation is almost as effective at lowering infections among both the student population and the general population as closing schools. Due to the continued testing of attending students, the overall infections in the general population are even lower in a school rotation scenario, showcasing the potential for emergent behaviors in agent-based models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Modeling and interactive simulation of measures against infection transmission

In this paper we develop an approach to modeling and simulating the process of infection transmission among individuals and the effectiveness of protective counter-measures. We base our approach on pedestrian dynamics and we implement it as an extension of the Vadere simulation framework. In order to enable a convenient simulation process for a variety of scenarios, we allow the user to interact with the simulated virtual environment (VE) during run time, for example, by dynamically opening/closing doors for room ventilation and moving/stopping agents for re-positioning their locations. We calibrate and evaluate our approach on a real-life case study—simulating COVID-19 infection transmission in two kinds of scenarios: large-scale (such as the city of Münster, Germany) and small-scale (such as the most common indoor environments—classrooms, restaurants, etc.). By using the tunable parameters of our modeling approach, we can simulate and predict the effectiveness of specific anti-COVID protective measures, such as social distancing, wearing masks, self-isolation, schools closing, etc. [ FROM AUTHOR] Copyright of Simulation is the property of Sage Publications, Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

An agent-based model of COVID-19 pandemic and its variants using fuzzy subsets and real data applied in an island environment

In this paper, we present a model of the spread of the COVID-19 pandemic simulated by a multi-agent system (MAS) based on demographic data and medical knowledge. Demographic data are linked to the distribution of the population according to age and to an index of socioeconomic fragility with regard to the elderly. Medical knowledge are related to two risk factors: age and obesity. The contributions of this approach are as follows. Firstly, the two aggravating risk factors are introduced into the MAS using fuzzy sets. Secondly, the worsening of disease caused by these risk factors is modeled by fuzzy aggregation operators. The appearance of virus variants is also introduced into the simulation through a simplified modeling of their contagiousness. Using real data from inhabitants of an island in the Antilles (Guadeloupe, FWI), we model the rate of the population at risk which could be critical cases, if neither social distancing nor barrier gestures are respected by the entire population. The results show that hospital capacities are exceeded. The results show that hospital capacities are exceeded. The socioeconomic fragility index is used to assess mortality and also shows that the number of deaths can be significant. © The Author(s), 2023. Published by Cambridge University Press.

An agent-based model to assess citizens' acceptance of COVID-19 restrictions

Italy was the first European state affected by COVID-19. Despite many uncertainties, citizens chose to trust the authorities and their trust was pivotal. This research aims to investigate the contribution of Italian citizens' trust in Public Institutions and how it influenced the acceptance of the necessary counter measures. Applying linear regression to a dataset of 4260 Italian respondents, we modelled trust from its main cognitive components, with particular reference to competence and willingness. Therefore, exploiting agent-based modelling, we investigated how these components affected trust and how trust evolution influences the acceptance of these restrictive measures. Our analysis confirms the key role of competence and willingness as cognitive components of trust. Results also suggest that a generic attempt to raise the average trust, besides being challenging, may not be the best strategy to increase compliance. Furthermore, reasoning at category level is a fundamental to identify the best components on which to invest. © Operational Research Society 2021.

An Intelligent Collaborative Image-Sensing System for Disease Detection

With the growth of smart medical devices and applications in smart hospitals, home care facilities, nursing, and the Internet of Medical Things (IoMT) are becoming more ubiquitous. It uses smart medical devices and cloud computing services, and basic Internet of Things (IoT) technology, to detect key body indicators, monitor health situations, and generate multivariate data to provide just-in-time healthcare services. In this article, we present a novel collaborative disease detection system based on IoMT amalgamated with captured image data. The system can be based on intelligent agents, where every agent explores the interaction between different medical data obtained by smart sensor devices using reinforcement learning as well as targets to detect diseases. The agents then collaborate to make a reliable conclusion about the detected diseases. Intensive experiments were conducted using medical data. The results show the importance of using intelligent agents for disease detection in healthcare decision-making. Moreover, collaboration increases the detection rate, with numerical results showing the superiority of the proposed framework compared with baseline solutions for disease detection. © 2001-2012 IEEE.

Impact of COVID-19 asymptomatic individuals on effective regenerative math by multi-agent simulation based on the SEAIR model

Various simulations are currently being conducted in response to the spread of the novel coronavirus infection. However, few multi-agent simulations have been conducted using a model that considers asymptomatic persons, who are one of the factors contributing to the spread of infection. In this study, we extended the SEAIR model, which considers asymptomatic persons, to multi-agent simulations to investigate the effect of the proportion of asymptomatic persons on the effective number of reproductions. The results indicate that asymptomatic persons may influence the number of positive groups at the peak of the spread of infection and the convergence period. © 2022 IEEE.

Developing Modern Agent Technologies in Combating Covid-19 Exposure: An Application in a Healthcare Facility

This study aims to identify the impact of adherence to Non-Pharmaceutical Interventions (NPI) such as facemask type Cotton Fabric Mask and social distancing on the rate of COVID-19 exposure in waiting areas inside an emergency department. As a methodology, a Multi-Agent Simulation approach was used to model and capture the flow of patients inside the emergency department in this research. Each agent represents a physical entity, including its attributes defined. These agents will collaborate based on the defined rules to achieve the best mimic of the system being modeled. This methodology aims to quantitatively evaluate the performance of preventive measures based on the agent's proximity and exposure time. The number of infections was affected by the application of the facemask. Infections were reduced when facemask adherence and social distancing were applied. The study showed that the application of social distancing has a similar effect to a 20% adherence of agents wearing a facemask. The model also reveals that more agents adhere to the facemask, and the time required to get an agent to the state exposed increases. Waiting areas are a potentially significant contributor to transmission. © 2022 IEEE.

Risk Assessment of Large-Scale Sports Events in the Context of COVID-19

This paper assesses the potential risks of epidemic situation and public opinion during the Beijing Winter Olympic Games by analyzing the epidemic situation and public opinion of the Tokyo Olympic Games. The results show that there is a strong time-lag correlation between the COVID-19 epidemic and the public opinion of the Tokyo Olympics. For the epidemic situation, the multi-agent modeling method is used at the city level to simulate the possible spread of diseases in the city where the event was held. At the Olympic village level, the modified the SEIR transmission model is modified to simulate the virus transmission in the Olympic Village during the Beijing Winter Olympic Games. At the end, the risk analysis of the Beijing Winter Olympic Games is carried out based on the time series prediction model. © 2022, Editorial Board of Journal of the University of Electronic Science and Technology of China. All right reserved.

School’s Out? Simulating Schooling Strategies During COVID-19

Multi-agent based systems offer the possibility to examine the effects of policies down to specific target groups while also considering the effects on a population-level scale. To examine the impact of different schooling strategies, an agent-based model is used in the context of the COVID-19 pandemic using a German city as an example. The simulation experiments show that reducing the class size by rotating weekly between in-person classes and online schooling is effective at preventing infections while driving up the detection rate among children through testing during weeks of in-person attendance. While open schools lead to higher infection rates, a surprising result of this study is that school rotation is almost as effective at lowering infections among both the student population and the general population as closing schools. Due to the continued testing of attending students, the overall infections in the general population are even lower in a school rotation scenario, showcasing the potential for emergent behaviors in agent-based models. © 2022, Springer Nature Switzerland AG.

A Model-based Multi-agent Framework to Enable an Agile Response to Supply Chain Disruptions

Due to the COVID-19 pandemic, the global supply chain is disrupted at an unprecedented scale under uncertain and unknown trends of labor shortage, high material prices, and changing travel or trade regulations. To stay competitive, enterprises desire agile and dynamic response strategies to quickly react to disruptions and recover supply-chain functions. Although both centralized and multi-agent approaches have been studied, their implementation requires prior knowledge of disruptions and agent-rule-based reasoning. In this paper, we introduce a model-based multi-agent framework that enables agent coordination and dynamic agent decision-making to respond to supply chain disruptions in an agile and effective manner. Through a small-scale simulated case study, we showcase the feasibility of the proposed approach under several disruption scenarios that affect a supply chain network differently, and analyze performance trade-offs between the proposed distributed and centralized methods. © 2022 IEEE.

From Research to Crisis Management: Multiagent Simulation for Local Governments

During the COVID-19 pandemic, a rise of (agent-based) simulation models for predicting future developments and assessing intervention scenarios has been observed. At the same time, dashboarding has become a popular way to aggregate and visualise large quantities of data. The AScore Pandemic Management Cockpit brings together multiagent-based simulation (MABS) and analysis functionalities for crisis managers. It combines the presentation of data and forecasting on the effects of containment measures in a modular, reusable architecture that streamlines the process of use for these non-researcher users. In this paper, the most successful features and concepts for the simplification of simulation usage are presented: definition of scenarios, limitation of parameters, and integrated result visualisation, all bundled in a web-based service to offer a low-barrier entry to the usage of MABS in decision-making processes. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Human Dense Avoidance Based on Coverage Control through Robots - A Patrol Algorithm Taking into Account of Visible Region

In this paper, we propose an efficient method for human dense avoidance based on a coverage control of multi-agent system. Our motivation is to contribute to an avoidance of human density in the current situation of COVID-19. We also aim to avoid crowding in social events and public spaces. Firstly, we consider a situation in which a robot autonomously patrols a region where human density occurs. As a main result, we propose a patrol algorithm in which robots distribute a cluster of humans by a coverage control if they discover them. Finally, we show an efficiency of the method based on a numerical simulation. © 2022 The Society of Instrument and Control Engineers - SICE.

Human Dense Avoidance Based on A Coverage Control through Robots

In this paper, we propose an efficient method for human dense avoidance based on a coverage control. Our motivation is to avoid crowding in public facilities such as stations and government offices, and human dense in the current situation of COVID-19 from system and control theory. In this paper, humans and robots are modelled as heterogeneous and homogeneous agents, respectively, which make decisions based on their local information. We suppose a dense situation caused by the rendezvous among humans due to their own inherent dynamics. As a main result, we propose a coverage control for a distributed movement of multiple humans. We also characterize the stationary point analytically in terms of the the gains which describe a strength of the interconnection of the agents, and the centers of the Voronoi regions related to the agents. Moreover, we verify the meaning of the characterization from an engineering viewpoint of the dense avoidance. Finally, we show the efficiency of the method based on a numerical simulation. © 2022 The Institute of Electrical Engineers of Japan.

Cost-Aware Dynamic Task Sharing Among Decentralized Autonomous Agents: Towards Dynamic Patient Sharing Among Hospitals

In the COVID-19 pandemic era, hospitals tend to be crowded with patients. Dynamic task sharing is becoming an important research theme and can be applied to patient sharing among hospitals. Unlike in standard task scheduling, the tasks are created dynamically and asynchronously, and each agent (hospital or region) is independent. Hence, we previously designed and compared the decentralized algorithms for dynamic task sharing. However, in these algorithms, the cost of task transfers was not considered. The cost of transferring a patient to a distant hospital is high and cannot be ignored. In this paper, we present new decentralized algorithms for dynamic task sharing that consider the cost of task transfers. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.