Total Number Of Agents Research Articles

Physicist's view on the unbalanced k-cardinality assignment problem.

The k-cardinality unbalanced assignment problem asks for assigning k "agents" to k "tasks" on a one-to-one basis, while minimizing the total cost associated with the assignment, with the total number of agents N and the total number of tasks M possibly different and larger than k. While many exact algorithms have been proposed to find such an optimal assignment, these methods are computationally prohibitive when the problem is large. We propose an approach to solving the k-cardinality assignment problem using techniques adapted from statistical physics. This paper provides a full description of this formalism, including all the proofs of its main claims. We derive a strongly concave free-energy function that captures the constraints of the k-assignment problem at a finite temperature. We prove that this free energy decreases monotonically as a function of β, the inverse of temperature, to the optimal assignment cost, providing a robust framework for temperature annealing. We also prove that for large enough β values the exact solution to the k-assignment problem can be derived using simple round-off to the nearest integer of the elements of the computed assignment matrix. We show that this framework can be adapted to handle degenerate k-assignment problems. We describe a computer implementation of our framework that is optimized for the GPU parallel architecture, using the library CUDA. This implementation is found to be as efficient as state-of-the-art implementations of parallel Hungarian algorithms on generic assignment problems, and orders of magnitude faster than those algorithms for pathological assignment cases.

Pedestrian evacuations with imitation of cooperative behavior.

We analyze the dynamics of room evacuation for mixed populations that include both competitive and cooperative individuals through numerical simulations using the social force model. Cooperative agents represent well-trained individuals who know how to behave in order to reduce risks within high-density crowds. We consider that competitive agents can imitate cooperative behavior when they are in close proximity to cooperators. We study the effects of the imitation of cooperative behavior on the duration and safety of evacuations, analyzing evacuation time and other quantities of interest for varying parameters such as the proportions of mixing, the aspect ratio of the room, and the parameters characterizing individual behaviors. Our main findings reveal that the addition of a relatively small number of cooperative agents into a crowd can reduce evacuation time and the density near the exit door, making the evacuation faster and safer despite an increase in the total number of agents. In particular, for long spaces such as corridors, a small number of added cooperative agents can significantly facilitate the evacuation process. We compare our results with those of systems without imitation and also study the general role of cooperation, providing further analysis for homogeneous populations. Our main conclusions emphasize the potential relevance of training people how to behave in high-density crowds.

Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos

The behaviour of multi agent learning in competitive network games is often studied within the context of zero sum games, in which convergence guarantees may be obtained. However, outside of this class the behaviour of learning is known to display complex behaviours and convergence cannot be always guaranteed. Nonetheless, in order to develop a complete picture of the behaviour of multi agent learning in competitive settings, the zero sum assumption must be lifted. Motivated by this we study the Q Learning dynamics, a popular model of exploration and exploitation in multi agent learning, in competitive network games. We determine how the degree of competition, exploration rate and network connectivity impact the convergence of Q Learning. To study generic competitive games, we parameterise network games in terms of correlations between agent payoffs and study the average behaviour of the Q Learning dynamics across all games drawn from a choice of this parameter. This statistical approach establishes choices of parameters for which Q Learning dynamics converge to a stable fixed point. Differently to previous works, we find that the stability of Q Learning is explicitly dependent only on the network connectivity rather than the total number of agents. Our experiments validate these findings and show that, under certain network structures, the total number of agents can be increased without increasing the likelihood of unstable or chaotic behaviours.

BPJS Employment Development Strategy for Ternate Branch in Increasing Acquisitions for Shield Agents

Social security is a form of social protection that guarantees everyone can fulfill a decent life's basic needs. Having death and accident insurance while working is very important for all non-formal workers in Indonesia, including in the city of Ternate and its surroundings. The data analysis method used in this research is descriptive qualitative. Qualitative descriptive is a method used to explore findings in the field. The research results show that there are four successful shield builders, such as the shield office built by Muhammad Hikmawan, which has 24 shield agents; Prasanti D has 25 shield agents; Taufik Hariyadi has 26 shield agents; and Vincenzo Runtu has 26 shield agents. The total number of agents from 4 supervisors is 101 productive shield agents who help socialize the benefits of the BPJS Employment program to the working community, non-wage earners. New BPJS Employment participants with the non-formal worker segment include motorcycle taxi drivers, fishermen, fishermen traders, etc. The acquisition sequence for January, there were 1048 participants; in February, there were 744 participants; in March, there were 5328 participants; in April, there were 2022 participants; in May, there were 7497 participants; and in June, there were 7188 participants; the total number of new participants registered through shield agents from January to June was 23827 participant.

Strategy‐proof size improvement: is it possible?*

AbstractThe number of assigned agents (i.e., size) is an important parameter in object allocations. While size maximality clashes with individual rationality and strategy‐proofness, it can still be possible to increase the size over a mechanism while keeping these properties. To pursue this research, we devise a size comparison criterion to investigate the possibility of size increase. A mechanism size‐wise dominates another mechanism if the latter never assigns more agents than the former, and at some problem, assigns more agents than . We obtain arguably mild conditions for a mechanism to not be dominated size‐wise by an individually rational and strategy‐proof mechanism. Moreover, whenever there are at least as many objects as the total number of agents, we find conditions, different from those previously mentioned, for a mechanism to not be dominated size‐wise by an individually rational and group strategy‐proof mechanism. These results have implications for deferred‐acceptance, top trading cycles, efficiency‐adjusted deferred‐acceptance, serial dictatorship, and Boston mechanisms.

Numerical Investigation on Reduction of Power Consumption and Improvement of Success Rate for Consensus in Multi‐Agent Systems over a Wireless Network Considering the Number of Agents

AbstractIn this paper, we investigate power adjustment for multi‐agent systems in a wireless network where communication range is limited. The approach in which communication range is dynamically changed is utilized so as to save power consumption. However, since drawback of this approach is that agents cannot expand their communication range, it causes that communication between agents tends to be disconnected. To overcome this problem, we propose two power adjustment methods. In the first method, communication range is temporarily expanded in accordance with the number of neighboring agents. In the second method, agents change their communication range by using information on the total number of agents and relative distance between an agent and the farthest neighboring agent. Through numerical simulation, we show that the proposed power adjustment methods reduce power consumption and improve success rate for consensus. © 2023 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Non-mean-field Vicsek-type models for collective behavior

We consider interacting particle dynamics with Vicsek-type interactions, and their macroscopic Partial Differential Equation (PDE) limit, in the non-mean-field regime; that is, we consider the case in which each particle/agent in the system interacts only with a prescribed subset of the particles in the system (for example, those within a certain distance). In this non-mean-field regime the influence between agents (i.e. the interaction term) can be normalized either by the total number of agents in the system (global scaling) or by the number of agents with which the particle is effectively interacting (local scaling). We compare the behavior of the globally scaled and the locally scaled systems in many respects, considering for each scaling both the PDE and the corresponding particle model. In particular, we observe that both the locally and globally scaled particle system exhibit pattern formation (i.e. formation of traveling-wave-like solutions) within certain parameter regimes, and generally display similar dynamics. The same is not true of the corresponding PDE models. Indeed, while both PDE models have multiple stationary states, for the globally scaled PDE such (space-homogeneous) equilibria are unstable for certain parameter regimes, with the instability leading to traveling wave solutions, while they are always stable for the locally scaled one, which never produces traveling waves. This observation is based on a careful numerical study of the model, supported by further analysis.

Distributed Task Allocation Algorithms for Multi-Agent Systems With Very Low Communication

In this paper we explore the problem of task allocation when communication is very low, e.g., when the probability of a successful message between agents is ≪ 0.01. Such situations may occur when agents choose not to communicate for reasons of stealth or when agent-to-agent communication is actively jammed by an adversary. In such cases, agents may need to divide tasks without knowing the locations of each other. Given the assumption that agents know the total number of agents in the workspace, we investigate solutions that ensure all tasks are eventually completed—even if some of the agents are destroyed. We present two task allocation algorithms that assume communication may not happen, but that benefit whenever communications are successful. (1) The Spatial Division Playbook Algorithm divides task among agents based on an area decomposition. (2) The Traveling Salesman Playbook Algorithm considers mission travel distance by leveraging Christofides’ 3/2 approximation algorithm. These algorithms have task completion runtime complexity of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i> log <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i> ) and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> ), respectively, where <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i> refers to the total number of tasks. We compare both algorithms to four state-of-the-art task allocation algorithms—ACBBA, DHBA, PIA and GA — across multiple communication levels and multiple numbers of targets, and using three different communication models. The new algorithms perform favorably, in terms of the time required to ensure all targets are visited, in the special case when communication is very low.

Resilient distributed vector consensus using centerpoint

In this paper, we study the resilient vector consensus problem in networks with adversarial agents and improve resilience guarantees of existing algorithms. A common approach to achieving resilient vector consensus is that every non-adversarial (or normal) agent in the network updates its state by moving towards a point in the convex hull of its normal neighbors’ states. Since an agent cannot distinguish between its normal and adversarial neighbors, computing such a point, often called safe point, is a challenging task. To compute a safe point, we propose to use the notion of centerpoint, which is an extension of the median in higher dimensions, instead of the Tverberg partition of points, which is often used for this purpose. We discuss that the notion of centerpoint provides a complete characterization of safe points in Rd. In particular, we show that a safe point is essentially an interior centerpoint if the number of adversaries in the neighborhood of a normal agent i is less than Nid+1, where d is the dimension of the state vector and Ni is the total number of agents in the neighborhood of i. Consequently, we obtain necessary and sufficient conditions on the number of adversarial agents to guarantee resilient vector consensus. Further, by considering the complexity of computing centerpoints, we discuss improvements in the resilience guarantees of vector consensus algorithms and compare with the other existing approaches. Finally, we numerically evaluate our approach.

Hybrid event‐triggered control of linear multiagent systems via a fully distributed approach

AbstractThis article studies the problem of event‐triggered consensus for linear multiagent systems. Leaderless and leader‐following cases are considered here. By adopting adaptive technology and utilizing the relationship between parameters, novel fully distributed control schemes are proposed. Both the control updates and the communication consumption between agents can be declined under the designed hybrid event‐triggered controller. Meanwhile, different from some existing event‐based control schemes, the projection operator is avoided so that the developed controllers use only local signal, which relies on neither the minimum nonzero eigenvalue of the Laplacian matrix nor the total number of agents. The designed control schemes can ensure that leaderless and leader‐following consensus to be achieved asymptotically, and Zeno behavior is excluded by presenting a hybrid event‐triggered mechanism. Simulation examples are provided to demonstrate the effectiveness of the presented control protocols.

Distributed Formation Estimation Via Pairwise Distance Measurements

Continuously and reliably estimating the relative configuration of robotic swarms in real-time constitutes a core functionality when pursuing the autonomy of such a swarm. Relying on external positioning systems, such as GPS or motion tracking systems, can provide the required information, but significantly limits the generality of an approach. In this letter, we target formation estimation for autonomous flights of swarms of small UAVs, as they pose particularly challenging restrictions on onboard resources, while opening up a large variety of practical scenarios for a multi-robot setup. While state-of-the-art has been addressing efficient formation estimation, scalability remains limited to only very few agents that can be handled in real-time, with the workload of each agent depending on the total number of agents in the swarm. Aiming for scalable multi-robot systems, here we propose a distributed formation estimation approach, where the computational load of each agent is decoupled from the swarm size. This approach is implemented in a setup with minimal communication effort, requiring only ego-motion estimates from each agent and pairwise distance measurements between them, constraining their configuration globally. Evaluations on swarms of up to 49 UAVs demonstrate the power of our approach to handle large swarms, while keeping the computational load bounded for individual agents and requiring only little data exchange between two robots.

Simulation-based Assessment of Data-Driven Processes in Customer Support Systems

The use of digital technology and data-driven techniques in companies has become an engine to transform operations, respond rapidly to customer demands, and enable new business models. However, companies face the challenge of measuring and evaluating how the introduction of new technology will impact operational processes. This paper takes a systems approach to study how to assess the trade-offs of adopting data-driven mechanisms to improve operational processes in a multichannel customer support system. We investigate potential cost savings from two technology applications: classification methods to direct customers to efficient self-service communication channels and routing methods to match customers with agents based on the query type and available skill set. Discrete event simulation experiments model and evaluate how lower-level technology adoption, characterized purely on a functional level, affects system-level performance. Resulting discussions include practical examples of how operational managers could use experimental information to make strategic operational decisions when adopting data-driven technologies. What-if scenarios combine distinct configurations of the customer classification mechanisms and the available communication channels, to evaluate the reduction in the total number of agents needed to meet a target service quality level.

Consensus of Linear Multiagent Systems With Input-Based Triggering Condition

This paper considers the consensus problem of multiagent systems with the input-based triggering condition. A model-based approach is first given to estimate the relative interagent states between intermittent communications instead of absolute states. A novel consensus protocol consisting of the relative interagent states is proposed for the consensus problem. Besides, compared with some results on the triggering condition consisting of state measurement error, a new triggering condition is constructed based on the control input. Then, the consensus protocol is executed by every agent in a fully distributed way, which has the advantage that the controller design is related to the number of agents instead of using global information. Moreover, the bounds of parameters of the controller and the triggering condition can be obtained by the proposed algorithm simultaneously, which depends on the total number of agents in multiagent networks. The proposed control scheme can ensure that states of all agents can achieve consensus. It is shown that “Zeno behavior” does not appear under the proposed algorithm. Finally, an illustrative example is given to verify the proposed method.

Consistent Tomography Under Partial Observations Over Adaptive Networks

This paper studies the problem of inferring whether an agent is directly influenced by another agent over a network. Agent $i$ influences agent $j$ if they are connected (according to the network topology), and if agent $j$ uses the data from agent $i$ to update its online learning algorithm. The solution of this inference task is challenging for two main reasons. First, only the output of the learning algorithm is available to the external observer that must perform the inference based on these indirect measurements. Second, only output measurements from a fraction of the network agents is available, with the total number of agents itself being also unknown. The main focus of this paper is ascertaining under these demanding conditions whether consistent tomography is possible , namely, whether it is possible to reconstruct the interaction profile of the observable portion of the network, with negligible error as the network size increases. We establish a critical achievability result, namely, that for symmetric combination policies and for any given fraction of observable agents, the interacting and non-interacting agent pairs split into two separate clusters as the network size increases. This remarkable property then enables the application of clustering algorithms to identify the interacting agents influencing the observations. We provide a set of numerical experiments that verify the results for finite network sizes and time horizons. The numerical experiments show that the results hold for asymmetric combination policies as well, which is particularly relevant in the context of causation .

Generation of Rule Bases of Fuzzy Systems Based on Modified Ant Colony Algorithms

This article is dedicated to the development and study of the method of generation of fuzzy systems rule bases of Mamdani-type with the formation of optimal consequents based on modified ant colony optimization algorithms. The obtained method makes it possible to effectively generate the rule bases with the optimal consequents for the Mamdani-type fuzzy systems in the following cases: at insufficient amount of initial information (under conditions of a high degree of information uncertainty); at a sufficiently large number of rules for which the development of a rule base based on the knowledge of experts is not always effective; at different levels of experts qualification. The study of the effectiveness of the proposed method in this work is carried out at the development of the rule base of the Mamdani-type fuzzy controller for the automatic control system of the reactor temperature of the specialized pyrolysis complex, that is intended for utilization of polymer waste. At the same time, the generation of the consequents of the rule base of this fuzzy controller was carried out with various adjustable parameters of the method, such as the total number of agents and the number of elite agents in the population. Based on the analysis of the results of the conducted experiments, the optimal configuration of the population of agents of the method was determined, for which the optimal vector of the consequents of the rule base can be found at the lowest computational and time costs. Also, the results of computer simulations of transients showed that the automatic temperature control system with the developed fuzzy controller rule base based on the proposed by the authors method with the optimal configuration of parameters has a significantly lower value of the objective function and higher control quality parameters than the system with the rule base on the basis of experts knowledge, which, in turn, confirms the high efficiency of this method.

Unreliable communication in high-performance distributed multi-agent systems: A ingenious scheme in high computing

Designing of distributed consensus algorithms featuring accuracy, robustness, reliability, and speed of convergence is in high demand for various multi-agent applications. In this research, it has been investigated to device a novel design of distributed estimation algorithm which can tackle the problem of unreliable communication among multi-agents to achieve consensus on the average value of their initial values and must be capable of computing the total number of agents in the system under dynamically changing interaction topologies. A dynamically changing network topology is considered in this research with unreliable communication links, and four different scenarios are established to be analyzed for the proposed consensus-based distributed estimation algorithm. This study established a consensus for a dynamically changing interaction topology among agents, for addition of agents in the network with dynamically switching topology at any instant in communication, for removal of agents from the network with dynamically switching topology at any instant in communication, and for a fixed topology with link failure and a reconnection with the same agent after each iteration. The proposed algorithm paces up the rate of convergence by reducing the number of iteration, along with sure convergence of the designed algorithm using the concepts of stochastic differential equation theory, control system theory, algebraic graph theory, and algebraic matrix theory. Finally, in the end, simulation results are provided which are clear evidence to validate the effectiveness of theoretical results of the proposed algorithm in comparison to previously known consensus algorithms in terms of different performance parameters.

A Novel Approach for Fast Average Consensus Under Unreliable Communication in Distributed Multi Agent Networks

In this research an algorithm is proposed to find the total number of agents participating in a multi agent network. Also to achieve hasten distributed average consensus in order to consider a network with reliable and unreliable communication links. Class of algorithm is considered in which fixed initial state values are assigned to all agents in the network, with the iterations they updates their initial values by communicating with their neighboring agents within a multi agent network. Algorithm with weighted matrix satisfy the convergence condition of average consensus and accelerate the method to achieve the consensus. Usually this convergence process is relatively sluggish and take moreover numerous iterations to achieve a consensus. To overcome the above issues, a new approach is proposed in order to minimize the rate of convergence. A two step algorithm has been proposed, where in step one each agent employs a linear predictor to predict future agent values. In second step the computed values are used to proceed further by the other agents to achieve consensus in order to bypass the redundant states. In the end proposed algorithm is compared with other existing consensus frameworks to strengthen the claim regarding the proposed two step algorithm which leads to escalate the rate of convergence and reduces the number of iterations.

A Three-Choice Minority Game Model with Homogeneous Agent Preferences for Resource Allocation

Microgrids have a promising potential to provide off-grid energy access for rural communities. With the growing interest on microgrids and energy access, there has been a renewed focus on developing demand management schemes appropriate for simple microgrids. One basic demand management concern is the problem of shaping consumer demand profiles such that peaks and troughs can be minimized. This problem can be viewed as a simplified resource allocation problem where each resource choice can only be chosen by a fixed number of agents. This study models the described allocation problem as a three-choice minority game where the resources available to the agents map to energy time-of-use windows. Agents were defined to have a homogeneous preference over these available choices of time windows. Different cost functions were likewise simulated in the game. The specific cost functions used in the simulations were chosen to determine whether agents can be influenced to self-organize such that the total number of agents per time window falls within a defined capacity. Results show that some cost functions successfully maintain agent numbers within the defined capacity. Nevertheless, results also indicate that agent gains may suffer when the capacity per choice is met.

DiMPP: a complete distributed algorithm for multi-agent path planning

Multi-agent path planning (MAPP) is a challenging task that aims to find conflict free paths for all the agents in a given domain. Priority-based decoupled approach is one of the several approaches to solve a MAPP problem. It works as follows: first, find paths of individual agents and then restructure these paths based on some priority of the agents. Most of the existing decoupled approaches use centralised algorithms. However, multi-agent systems are inherently distributed, where agents have limited information and each agent may not know the total number of agents in the system. Some of these aspects are incorporated in DMAPP. DMAPP is an existing fully distributed algorithm that works in three phases: (i) individual path planning, (ii) priority decision-making and (iii) plan restructuring. However, DMAPP is incomplete, i.e. DMAPP may fail to find a solution, even if it exists. In this paper, we present a new distributed algorithm (DiMPP) which is complete. The computer simulations performed on some well-known benchmark domains reveal that DiMPP outperforms DMAPP in the number of problem instances solved. For larger problem instances, the time taken by DiMPP is orders of magnitude less than that of some existing centralised algorithms.

Conformity in voting

A group of agents has to decide whether to accept or reject a proposal. Agents vote in favor of or against the proposal and, if the number of agents in favor is greater than a certain threshold, the proposal is accepted. Conformist agents vote based on not only their opinion but also the votes of other agents. Independent agents consider only their own opinions. If all agents are conformists and vote simultaneously, there are undominated Nash equilibria in which the decision is different from that obtained if all agents vote for their opinions. Next, we provide the number of independent agents sufficient to obtain, in any equilibrium, the decision obtained when all agents vote for their opinions. This number depends on the total number of agents, the threshold, and the conformity measure. If agents vote sequentially, the voting behavior of conformist agents does not affect the decision.