Siga este enlace para ver otros tipos de publicaciones sobre el tema: Interaction multi-agents.
Artículos de revistas sobre el tema "Interaction multi-agents"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores artículos de revistas para su investigación sobre el tema "Interaction multi-agents".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore artículos de revistas sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
1
Sherstyugina, Anastasiya, and Roman Nesterov. "Discovering Process Models from Event Logs of Multi-Agent Systems Using Event Relations." Proceedings of the Institute for System Programming of the RAS 35, no. 3 (2023): 11–32. http://dx.doi.org/10.15514/ispras-2023-35(3)-1.
Texto completoResumen
The structure of a process model directly discovered from an event log of a multi-agent system often does not reflect the behavior of individual agents and their interactions. We suggest analyzing the relations between events in an event log to localize actions executed by different agents and involved in their asynchronous interaction. Then, a process model of a multi-agent system is composed from individual agent models between which we add channels to model the asynchronous message exchange. We consider agent interaction within the acyclic and cyclic behavior of different agents. We develop an algorithm that supports the analysis of event relations between different interacting agents and study its correctness. Experimental results demonstrate the overall improvement in the quality of process models discovered by the proposed approach in comparison to monolithic models discovered directly from event logs of multiagent systems.
2
Liu, Yong, Weixun Wang, Yujing Hu, Jianye Hao, Xingguo Chen, and Yang Gao. "Multi-Agent Game Abstraction via Graph Attention Neural Network." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (2020): 7211–18. http://dx.doi.org/10.1609/aaai.v34i05.6211.
Texto completoResumen
In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent systems, the interactions between agents often happen locally, which means that agents neither need to coordinate with all other agents nor need to coordinate with others all the time. Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents. However, the methods cannot be directly used in a large-scale environment due to the difficulty of transforming the complex interactions between agents into rules. In this paper, we model the relationship between agents by a complete graph and propose a novel game abstraction mechanism based on two-stage attention network (G2ANet), which can indicate whether there is an interaction between two agents and the importance of the interaction. We integrate this detection mechanism into graph neural network-based multi-agent reinforcement learning for conducting game abstraction and propose two novel learning algorithms GA-Comm and GA-AC. We conduct experiments in Traffic Junction and Predator-Prey. The results indicate that the proposed methods can simplify the learning process and meanwhile get better asymptotic performance compared with state-of-the-art algorithms.
3
Bucher, Andreas, Mateusz Dolata, Sven Eckhardt, Dario Staehelin, and Gerhard Schwabe. "Talking to Multi-Party Conversational Agents in Advisory Services: Command-based vs. Conversational Interactions." Proceedings of the ACM on Human-Computer Interaction 8, GROUP (2024): 1–25. http://dx.doi.org/10.1145/3633072.
Texto completoResumen
Interacting with a conversational agent (CA) is becoming a major paradigm for human-technology interaction. Yet, ways for interacting with CAs are still forming, especially in situations involving more than one human. Starting an interaction with a CA might involve a wakeword and command. Alternatively, it could become active based on implicit requests and context information. Hence, CA designers face a serious dilemma: explicit commands disturb a natural conversation flow, while implicit requests might cause inadequate CA behavior. This study explores this dilemma and discusses observations from a project featuring a CA for financial advisory services. Advisors initially envisioned a CA that ''blends with the background'' and acts on context information. However, when engaging with a CA, they used conversational interactions in one part of the encounter and command-based interactions in another. We discuss this observation and contrast it against previous literature. This insight has implications for design and research.
4
Li, Guangyu, Bo Jiang, Hao Zhu, Zhengping Che, and Yan Liu. "Generative Attention Networks for Multi-Agent Behavioral Modeling." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (2020): 7195–202. http://dx.doi.org/10.1609/aaai.v34i05.6209.
Texto completoResumen
Understanding and modeling behavior of multi-agent systems is a central step for artificial intelligence. Here we present a deep generative model which captures behavior generating process of multi-agent systems, supports accurate predictions and inference, infers how agents interact in a complex system, as well as identifies agent groups and interaction types. Built upon advances in deep generative models and a novel attention mechanism, our model can learn interactions in highly heterogeneous systems with linear complexity in the number of agents. We apply this model to three multi-agent systems in different domains and evaluate performance on a diverse set of tasks including behavior prediction, interaction analysis and system identification. Experimental results demonstrate its ability to model multi-agent systems, yielding improved performance over competitive baselines. We also show the model can successfully identify agent groups and interaction types in these systems. Our model offers new opportunities to predict complex multi-agent behaviors and takes a step forward in understanding interactions in multi-agent systems.
5
de Hauwere, Yann-Michaël, Sam Devlin, Daniel Kudenko, and Ann Nowé. "Context-sensitive reward shaping for sparse interaction multi-agent systems." Knowledge Engineering Review 31, no. 1 (2016): 59–76. http://dx.doi.org/10.1017/s0269888915000193.
Texto completoResumen
AbstractPotential-based reward shaping is a commonly used approach in reinforcement learning to direct exploration based on prior knowledge. Both in single and multi-agent settings this technique speeds up learning without losing any theoretical convergence guarantees. However, if speed ups through reward shaping are to be achieved in multi-agent environments, a different shaping signal should be used for each context in which agents have a different subgoal or when agents are involved in a different interaction situation.This paper describes the use of context-aware potential functions in a multi-agent system in which the interactions between agents are sparse. This means that, unknown to the agentsa priori, the interactions between the agents only occur sporadically in certain regions of the state space. During these interactions, agents need to coordinate in order to reach the global optimal solution.We demonstrate how different reward shaping functions can be used on top of Future Coordinating Q-learning (FCQ-learning); an algorithm capable of automatically detecting when agents should take each other into consideration. Using FCQ-learning, coordination problems can even be anticipated before the actual problems occur, allowing the problems to be solved timely. We evaluate our approach on a range of gridworld problems, as well as a simulation of air traffic control.
6
Emelyanov, Viktor V. "Organization of the Agents Interaction in Multi-Agents of Production Coordination System." IFAC Proceedings Volumes 33, no. 17 (2000): 485–89. http://dx.doi.org/10.1016/s1474-6670(17)39450-8.
Texto completo
7
Dushkin, Roman. "Multi-agent systems for cooperative ITS." Тренды и управление, no. 1 (January 2021): 42–50. http://dx.doi.org/10.7256/2454-0730.2021.1.34169.
Texto completoResumen
This article presents an original perspective upon the problem of creating intelligent transport systems in the conditions of using highly automated vehicles that freely move on the urban street-road networks. The author explores the issues of organizing a multi-agent system from such vehicles for solving the higher level tasks rather than by an individual agent (in this case – by a vehicle). Attention is also given to different types of interaction between the vehicles or vehicles and other agents. The examples of new tasks, in which the arrangement of such interaction would play a crucial role, are described. The scientific novelty is based on the application of particular methods and technologies of the multi-agent systems theory from the field of artificial intelligence to the creation of intelligent transport systems and organizing free-flow movement of highly automated vehicles. It is demonstrated the multi-agent systems are able to solve more complex tasks than separate agents or a group of non-interacting agents. This allows obtaining the emergent effects of the so-called swarm intelligence of the multiple interacting agents. This article may be valuable to everyone interested in the future of the transport sector.
8
ZHANG, Kun, Yoichiro MAEDA, and Yasutake TAKAHASHI. "Learning Model Considering the Interaction among Heterogeneous Multi-Agents." Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 24, no. 5 (2012): 1002–11. http://dx.doi.org/10.3156/jsoft.24.1002.
Texto completo
9
Zhang, Kun, Yoichiro Maeda, and Yasutake Takahashi. "Group Behavior Learning in Multi-Agent Systems Based on Social Interaction Among Agents." Journal of Advanced Computational Intelligence and Intelligent Informatics 15, no. 7 (2011): 896–903. http://dx.doi.org/10.20965/jaciii.2011.p0896.
Texto completoResumen
Research on multi-agent systems, in which autonomous agents are able to learn cooperative behavior, has been the subject of rising expectations in recent years. We have aimed at the group behavior generation of the multi-agents who have high levels of autonomous learning ability, like that of human beings, through social interaction between agents to acquire cooperative behavior. The sharing of environment states can improve cooperative ability, and the changing state of the environment in the information shared by agents will improve agents’ cooperative ability. On this basis, we use reward redistribution among agents to reinforce group behavior, and we propose a method of constructing a multi-agent system with an autonomous group creation ability. This is able to strengthen the cooperative behavior of the group as social agents.
10
Jin, Kun, Yevgeniy Vorobeychik, and Mingyan Liu. "Multi-Scale Games: Representing and Solving Games on Networks with Group Structure." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 6 (2021): 5497–505. http://dx.doi.org/10.1609/aaai.v35i6.16692.
Texto completoResumen
Network games provide a natural machinery to compactly represent strategic interactions among agents whose payoffs exhibit sparsity in their dependence on the actions of others. Besides encoding interaction sparsity, however, real networks often exhibit a multi-scale structure, in which agents can be grouped into communities, those communities further grouped, and so on, and where interactions among such groups may also exhibit sparsity. We present a general model of multi-scale network games that encodes such multi-level structure. We then develop several algorithmic approaches that leverage this multi-scale structure, and derive sufficient conditions for convergence of these to a Nash equilibrium. Our numerical experiments demonstrate that the proposed approaches enable orders of magnitude improvements in scalability when computing Nash equilibria in such games. For example, we can solve previously intractable instances involving up to 1 million agents in under 15 minutes.
11
Benoudina, Lazhar, and Mohammed RedjimiRedjimi. "Multi Agent System Based Approach for Industrial Process Simulation." Journal Européen des Systèmes Automatisés 54, no. 2 (2021): 209–17. http://dx.doi.org/10.18280/jesa.540202.
Texto completoResumen
Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.
12
Penner, Robin R. "Multi-Agent Societies for Collaborative Interaction." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 40, no. 15 (1996): 762–66. http://dx.doi.org/10.1177/154193129604001503.
Texto completoResumen
The application of a multi-agent architecture to the design and operation of automated process management systems is proving to be a fruitful method of facilitating human-system collaboration. The agent architecture we are developing is intended to be applied in environments where humans and automated systems jointly perform information intensive tasks, and is based on an organization of multiple agents, where both human and software agents are integrated members in groups akin to human societies. Important features of our architecture include an organization based on social structures, a user interface model based on a collaborative interaction metaphors, and a situated action paradigm for agent behavior.
13
Jiang, Min, Zhiqing Meng, Xinsheng Xu, Rui Shen, and Gengui Zhou. "Multiobjective Interaction Programming Problem with Interaction Constraint for Two Players." Mathematical Problems in Engineering 2012 (2012): 1–14. http://dx.doi.org/10.1155/2012/618928.
Texto completoResumen
This paper extends an existing cooperative multi-objective interaction programming problem with interaction constraint for two players (or two agents). First, we define ans-optimal joint solution with weight vector to multi-objective interaction programming problem with interaction constraint for two players and get some properties of it. It is proved that thes-optimal joint solution with weight vector to the multi-objective interaction programming problem can be obtained by solving a corresponding mathematical programming problem. Then, we define anothers-optimal joint solution with weight value to multi-objective interaction programming problem with interaction constraint for two players and get some of its properties. It is proved that thes-optimal joint solution with weight vector to multi-objective interaction programming problem can be obtained by solving a corresponding mathematical programming problem. Finally, we build a pricing multi-objective interaction programming model for a bi-level supply chain. Numerical results show that the interaction programming pricing model is better than Stackelberg pricing model and the joint pricing model.
14
Schmidt, Susanne, Oscar Ariza, and Frank Steinicke. "Intelligent Blended Agents: Reality–Virtuality Interaction with Artificially Intelligent Embodied Virtual Humans." Multimodal Technologies and Interaction 4, no. 4 (2020): 85. http://dx.doi.org/10.3390/mti4040085.
Texto completoResumen
Intelligent virtual agents (VAs) already support us in a variety of everyday tasks such as setting up appointments, monitoring our fitness, and organizing messages. Adding a humanoid body representation to these mostly voice-based VAs has enormous potential to enrich the human–agent communication process but, at the same time, raises expectations regarding the agent’s social, spatial, and intelligent behavior. Embodied VAs may be perceived as less human-like if they, for example, do not return eye contact, or do not show a plausible collision behavior with the physical surroundings. In this article, we introduce a new model that extends human-to-human interaction to interaction with intelligent agents and covers different multi-modal and multi-sensory channels that are required to create believable embodied VAs. Theoretical considerations of the different aspects of human–agent interaction are complemented by implementation guidelines to support the practical development of such agents. In this context, we particularly emphasize one aspect that is distinctive of embodied agents, i.e., interaction with the physical world. Since previous studies indicated negative effects of implausible physical behavior of VAs, we were interested in the initial responses of users when interacting with a VA with virtual–physical capabilities for the first time. We conducted a pilot study to collect subjective feedback regarding two forms of virtual–physical interactions. Both were designed and implemented in preparation of the user study, and represent two different approaches to virtual–physical manipulations: (i) displacement of a robotic object, and (ii) writing on a physical sheet of paper with thermochromic ink. The qualitative results of the study indicate positive effects of agents with virtual–physical capabilities in terms of their perceived realism as well as evoked emotional responses of the users. We conclude with an outlook on possible future developments of different aspects of human–agent interaction in general and the physical simulation in particular.
15
Aman, Bogdan, and Gabriel Ciobanu. "Knowledge Dynamics and Behavioural Equivalences in Multi-Agent Systems." Mathematics 9, no. 22 (2021): 2869. http://dx.doi.org/10.3390/math9222869.
Texto completoResumen
We define a process calculus to describe multi-agent systems with timeouts for communication and mobility able to handle knowledge. The knowledge of an agent is represented as sets of trees whose nodes carry information; it is used to decide the interactions with other agents. The evolution of the system with exchanges of knowledge between agents is presented by the operational semantics, capturing the concurrent executions by a multiset of actions in a labelled transition system. Several results concerning the relationship between the agents and their knowledge are presented. We introduce and study some specific behavioural equivalences in multi-agent systems, including a knowledge equivalence able to distinguish two systems based on the interaction of the agents with their local knowledge.
16
Ababii, Victor, Viorica Sudacevschi, Silvia Munteanu, Ana Turcan, and Olesea Borozan. "Decision-Making Support System for Quality Smart City Services." International Journal of Progressive Sciences and Technologies 39, no. 1 (2023): 450. http://dx.doi.org/10.52155/ijpsat.v39.1.5436.
Texto completoResumen
This paper presents the results of research carried out in the field of developing decision support systems for quality Smart City services. The decision-making system consists of two sets of Agents: Service Provider Agents and Service Consumer Agents. The interaction between the Agent sets is governed by the knowledge base which is managed by the Service Quality Assessors. Service quality is evaluated based on a Multi-Objective Optimization model competitively performed by applying game theory (Nash Equilibrium) between Agent sets involving available resources and knowledge. The paper developed: interaction diagram between Agents and services offered by Smart City, interaction diagram between sets of Agents to provide quality services, and multi-level infrastructure diagram for decision support system. The Multi-Objective Optimization problem is defined in the form of the set of objective functions for the evaluation of service quality and the set of constraint functions for service state parameters and action parameters for service provision.
17
Serrano, Emilio, and Javier Bajo. "Discovering Hidden Mental States in Open Multi-Agent Systems by Leveraging Multi-Protocol Regularities with Machine Learning." Sensors 20, no. 18 (2020): 5198. http://dx.doi.org/10.3390/s20185198.
Texto completoResumen
The agent paradigm and multi-agent systems are a perfect match for the design of smart cities because of some of their essential features such as decentralization, openness, and heterogeneity. However, these major advantages also come at a great cost. Since agents’ mental states are hidden when the implementation is not known and available, intelligent services of smart cities cannot leverage information from them. We contribute with a proposal for the analysis and prediction of hidden agents’ mental states in a multi-agent system using machine learning methods that learn from past agents’ interactions. The approach employs agent communication languages, which is a core property of these multi-agent systems, to infer theories and models about agents’ mental states that are not accessible in an open system. These mental state models can be used on their own or combined to build protocol models, allowing agents (and their developers) to predict future agents’ behavior for various tasks such as testing and debugging them or making communications more efficient, which is essential in an ambient intelligence environment. This paper’s main contribution is to explore the problem of building these agents’ mental state models not from one, but from several interaction protocols, even when the protocols could have different purposes and provide distinct ambient intelligence services.
18
Cliff, Oliver M., Joseph T. Lizier, X. Rosalind Wang, Peter Wang, Oliver Obst, and Mikhail Prokopenko. "Quantifying Long-Range Interactions and Coherent Structure in Multi-Agent Dynamics." Artificial Life 23, no. 1 (2017): 34–57. http://dx.doi.org/10.1162/artl_a_00221.
Texto completoResumen
We develop and apply several novel methods quantifying dynamic multi-agent team interactions. These interactions are detected information-theoretically and captured in two ways: via (i) directed networks (interaction diagrams) representing significant coupled dynamics between pairs of agents, and (ii) state-space plots (coherence diagrams) showing coherent structures in Shannon information dynamics. This model-free analysis relates, on the one hand, the information transfer to responsiveness of the agents and the team, and, on the other hand, the information storage within the team to the team's rigidity and lack of tactical flexibility. The resultant interaction and coherence diagrams reveal implicit interactions, across teams, that may be spatially long-range. The analysis was verified with a statistically significant number of experiments (using simulated football games, produced during RoboCup 2D Simulation League matches), identifying the zones of the most intense competition, the extent and types of interactions, and the correlation between the strength of specific interactions and the results of the matches.
19
Telnov, Yu F., A. V. Danilov, R. I. Diveev, V. A. Kazakov, and E. V. Yaroshenko. "Development of a prototype of multi-agent system of network interaction of educational institutions." Open Education 22, no. 6 (2019): 14–26. http://dx.doi.org/10.21686/1818-4243-2018-6-14-26.
Texto completoResumen
The aim of the researchis to develop a prototype of the intelligent multi-agent system for dynamic interaction of the intelligent agents in the integrated information and educational space to solve the problem of formation of joint educational programs by several educational institutions.Materials and methods.In modern conditions of digital transformation of education the organization of network training of students on dynamically formed educational programs in accordance with the needs of the labor market and the individual requirements of students is becoming increasingly important. It is proposed to develop a software platform based on intelligent multi-agent technology for flexible integration of educational resources and implementation of joint educational programs by several interacting educational institutions. As a basis for the development of the software prototype architecture, the specifications of the developer community for the standardization of agent technologies FIPA (the Foundation for Intelligent Physical Agents), and the software tool environment – JADE framework (Java Agent Development Network) were chosen.Results.The paper presents the architecture of intelligent multi-agent system for network interaction of educational institutions in the integrated information and educational space, which allows to dynamically forming educational programs in accordance with the requested professional competencies. The structure of the ontology of information and educational space, providing the interaction of intelligent agents, is justified, and the mechanism of its display from the OWL format to the format of the tool environment JADE, using the plugin Protege is described. The description of the software prototype, the structure of intelligent agents in the JADE format and the technology of agent interaction, based on the FIPA protocols in the process of educational programs formation is presented.Conclusion.The implementation of the multi-agent system prototype for network interaction of educational institutions allows you to quickly create educational programs in accordance with individual and group learning trajectories under the specific formed professional competence. The presented software prototype with some modification can be used for other subject areas of the digital economy, involving the dynamic formation of network structures of interaction for business partners.
20
Xu, Tian, Hui Zhang, and Chen Yu. "Cooperative gazing behaviors in human multi-robot interaction." Interaction Studies 14, no. 3 (2013): 390–418. http://dx.doi.org/10.1075/is.14.3.05xu.
Texto completoResumen
When humans are addressing multiple robots with informative speech acts (Clark & Carlson 1982), their cognitive resources are shared between all the participating robot agents. For each moment, the user’s behavior is not only determined by the actions of the robot that they are directly gazing at, but also shaped by the behaviors from all the other robots in the shared environment. We define cooperative behavior as the action performed by the robots that are not capturing the user’s direct attention. In this paper, we are interested in how the human participants adjust and coordinate their own behavioral cues when the robot agents are performing different cooperative gaze behaviors. A novel gaze-contingent platform was designed and implemented. The robots’ behaviors were triggered by the participant’s attentional shifts in real time. Results showed that the human participants were highly sensitive when the robot agents were performing different cooperative gazing behaviors. Keywords: human-robot interaction; multi-robot interaction; multiparty interaction; eye gaze cue; embodied conversational agent
21
Yesikova, Tatyana, and Svetlana Vakhrusheva. "ASSESSMENT OF CONSEQUENCES OF IMPLEMENTATION OF LARGE-SCALE INFRASTRUCTURE PROJECTS BASED ON THE AGENT APPROACH: TOPOLOGY OF THE MULTIAGENT SYSTEM." Interexpo GEO-Siberia 3, no. 1 (2019): 109–16. http://dx.doi.org/10.33764/2618-981x-2019-3-1-109-116.
Texto completoResumen
The article poses the problem of modeling processes associated with the construction of large-scale infrastructural projects in the context of the Bering Strait tunnel (road construction in the Far North). The purpose of the simulation is to identify potential problems and estimate losses for various participants in similar projects. The study is based on such a simulation method as multi-agent modeling. The article describes the basics of building the topology of a multi-agent system in relation to this task: decomposing a process into subprocesses, identifying the main active agents, describing of the characteristics (attributes) of these agents, determining the type of their interaction. The article also presents a graph that is the prototype of a multi-agent system for a specific subject area and a description of the interactions of the identified agents.
22
Li, Jing, and Yue Jin Zhou. "Simulation of Conflicts Resolution in Virtual Teams." Advanced Materials Research 187 (February 2011): 39–44. http://dx.doi.org/10.4028/www.scientific.net/amr.187.39.
Texto completoResumen
The purpose of the paper is to study the conflict resolution in virtual teams. Multi-agent technology is used to simulate the virtual team. In the team, agents adapt the Q-learning algorithm to adjust their behaviors. Through the interaction of virtual members, part of conflicts can be resolved by team members. The experiments are manipulated to study the process of the interaction in the team. The results of experiments show a new rule for conflict resolution emerged from the dynamic interactions of agents. The conclusions show significance on the management of team in real world.
23
Li, Tongyue, Dianxi Shi, Songchang Jin, Zhen Wang, Huanhuan Yang, and Yang Chen. "Multi-Agent Hierarchical Graph Attention Actor–Critic Reinforcement Learning." Entropy 27, no. 1 (2024): 4. https://doi.org/10.3390/e27010004.
Texto completoResumen
Multi-agent systems often face challenges such as elevated communication demands, intricate interactions, and difficulties in transferability. To address the issues of complex information interaction and model scalability, we propose an innovative hierarchical graph attention actor–critic reinforcement learning method. This method naturally models the interactions within a multi-agent system as a graph, employing hierarchical graph attention to capture the complex cooperative and competitive relationships among agents, thereby enhancing their adaptability to dynamic environments. Specifically, graph neural networks encode agent observations as single feature-embedding vectors, maintaining a constant dimensionality irrespective of the number of agents, which improves model scalability. Through the “inter-agent” and “inter-group” attention layers, the embedding vector of each agent is updated into an information-condensed and contextualized state representation, which extracts state-dependent relationships between agents and model interactions at both individual and group levels. We conducted experiments across several multi-agent tasks to assess our proposed method’s effectiveness, stability, and scalability. Furthermore, to enhance the applicability of our method in large-scale tasks, we tested and validated its performance within a curriculum learning training framework, thereby enhancing its transferability.
24
Olaru, Andrei, and Monica Pricope. "Multi-Modal Decentralized Interaction in Multi-Entity Systems." Sensors 23, no. 6 (2023): 3139. http://dx.doi.org/10.3390/s23063139.
Texto completoResumen
Current multi-agent frameworks usually use centralized, fixed communication infrastructures for the entities that are deployed using them. This decreases the robustness of the system but is less challenging when having to deal with mobile agents that can migrate between nodes. We introduce, in the context of the FLASH-MAS (Fast and Lightweight Agent Shell) multi-entity deployment framework, methods to build decentralized interaction infrastructures which support migrating entities. We discuss the WS-Regions (WebSocket Regions) communication protocol, a proposal for interaction in deployments using multiple communication methods, and a mechanism to facilitate using arbitrary names for entities. The WS-Regions Protocol is compared against Jade (the Java Agent Development Framework), the most popular agent deployment framework, with a favorable trade-off between decentralization and performance.
25
Lavendelis, Egons, and Janis Grundspenkis. "Design of Multi-Agent Based Intelligent Tutoring Systems." Scientific Journal of Riga Technical University. Computer Sciences 38, no. 38 (2009): 48–59. http://dx.doi.org/10.2478/v10143-009-0004-z.
Texto completoResumen
Design of Multi-Agent Based Intelligent Tutoring SystemsResearch of two fields, namely agent oriented software engineering and intelligent tutoring systems, have to be taken into consideration, during the design of multi-agent based intelligent tutoring systems (ITS). Thus there is a need for specific approaches for agent based ITS design, which take into consideration main ideas from both fields. In this paper we propose a top down design approach for multi-agent based ITSs. The proposed design approach consists of the two main stages: external design and internal design of agents. During the external design phase the behaviour of agents and interactions among them are designed. The following steps are done: task modelling and task allocation to agents, use case map creation, agent interaction design, ontology creation and holon design. During the external design phase agents and holons are defined according to the holonic multi-agent architecture for ITS development. During the internal design stage the internal structure of agents is specified. The internal structure of each agent is represented in the specific diagram, called internal view of the agent, consisting of agent's actions and interactions among them, rules for incoming message and perception processing, incoming and outgoing messages, and beliefs of the agent. The proposed approach is intended to be a part of the full life cycle methodology for multi-agent based ITS development. The approach is developed using the same concepts as JADE agent platform and is suitable for agent code generation from the design diagrams.
26
Calliess, Jan-P., and Stephen Roberts. "Multi-Agent Planning with Mixed-Integer Programming and Adaptive Interaction Constraint Generation (Extended Abstract)." Proceedings of the International Symposium on Combinatorial Search 4, no. 1 (2021): 207–8. http://dx.doi.org/10.1609/socs.v4i1.18304.
Texto completoResumen
We consider multi-agent planning in which the agents' optimal plans are solutions to mixed-integer programs (MIP) that are coupled via integer constraints. While in principle, one could find the joint solution by combining the separate problems into one large joint centralized MIP, this approach rapidly becomes intractable for growing numbers of agents and large problem domains. To address this issue, we propose an iterative approach that combines conflict detection with constraint-generation whereby the agents plan repeatedly until all conflicts are resolved. In each planning iteration, the agents plan with as few other agents and interaction-constraints as possible. This yields an optimal method that can reduce computation markedly. We test our approach in the context of multi-agent collision avoidance in graphs with indivisible flows. Our initial simulations on randomized graph routing problems confirm predicted optimality and reduced computational effort.
27
Wang, Haixing, Yi Yang, Zhiwei Lin, and Tian Wang. "Multi-Agent Reinforcement Learning with Optimal Equivalent Action of Neighborhood." Actuators 11, no. 4 (2022): 99. http://dx.doi.org/10.3390/act11040099.
Texto completoResumen
In a multi-agent system, the complex interaction among agents is one of the difficulties in making the optimal decision. This paper proposes a new action value function and a learning mechanism based on the optimal equivalent action of the neighborhood (OEAN) of a multi-agent system, in order to obtain the optimal decision from the agents. In the new Q-value function, the OEAN is used to depict the equivalent interaction between the current agent and the others. To deal with the non-stationary environment when agents act, the OEAN of the current agent is inferred simultaneously by the maximum a posteriori based on the hidden Markov random field model. The convergence property of the proposed methodology proved that the Q-value function can approach the global Nash equilibrium value using the iteration mechanism. The effectiveness of the method is verified by the case study of the top-coal caving. The experiment results show that the OEAN can reduce the complexity of the agents’ interaction description, meanwhile, the top-coal caving performance can be improved significantly.
28
Dubenko, Yu V. "ANALYTICAL REVIEW OF MULTI-AGENT REINFORCEMENT LEARNING PROBLEMS." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 192 (June 2020): 48–56. http://dx.doi.org/10.14489/vkit.2020.06.pp.048-056.
Texto completoResumen
This paper is devoted to the problem of collective artificial intelligence in solving problems by intelligent agents in external environments. The environments may be: fully or partially observable, deterministic or stochastic, static or dynamic, discrete or continuous. The paper identifies problems of collective interaction of intelligent agents when they solve a class of tasks, which need to coordinate actions of agent group, e. g. task of exploring the territory of a complex infrastructure facility. It is revealed that the problem of reinforcement training in multi-agent systems is poorly presented in the press, especially in Russian-language publications. The article analyzes reinforcement learning, describes hierarchical reinforcement learning, presents basic methods to implement reinforcement learning. The concept of macro-action by agents integrated in groups is introduced. The main problems of intelligent agents collective interaction for problem solving (i. e. calculation of individual rewards for each agent; agent coordination issues; application of macro actions by agents integrated into groups; exchange of experience generated by various agents as part of solving a collective problem) are identified. The model of multi-agent reinforcement learning is described in details. The article describes problems of this approach building on existing solutions. Basic problems of multi-agent reinforcement learning are formulated in conclusion.
29
Dubenko, Yu V. "ANALYTICAL REVIEW OF MULTI-AGENT REINFORCEMENT LEARNING PROBLEMS." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 192 (June 2020): 48–56. http://dx.doi.org/10.14489/vkit.2020.06.pp.048-056.
Texto completoResumen
This paper is devoted to the problem of collective artificial intelligence in solving problems by intelligent agents in external environments. The environments may be: fully or partially observable, deterministic or stochastic, static or dynamic, discrete or continuous. The paper identifies problems of collective interaction of intelligent agents when they solve a class of tasks, which need to coordinate actions of agent group, e. g. task of exploring the territory of a complex infrastructure facility. It is revealed that the problem of reinforcement training in multi-agent systems is poorly presented in the press, especially in Russian-language publications. The article analyzes reinforcement learning, describes hierarchical reinforcement learning, presents basic methods to implement reinforcement learning. The concept of macro-action by agents integrated in groups is introduced. The main problems of intelligent agents collective interaction for problem solving (i. e. calculation of individual rewards for each agent; agent coordination issues; application of macro actions by agents integrated into groups; exchange of experience generated by various agents as part of solving a collective problem) are identified. The model of multi-agent reinforcement learning is described in details. The article describes problems of this approach building on existing solutions. Basic problems of multi-agent reinforcement learning are formulated in conclusion.
30
Bertaglia, Giulia, Lorenzo Pareschi, and Giuseppe Toscani. "Modelling contagious viral dynamics: a kinetic approach based on mutual utility." Mathematical Biosciences and Engineering 21, no. 3 (2024): 4241–68. http://dx.doi.org/10.3934/mbe.2024187.
Texto completoResumen
<abstract><p>The temporal evolution of a contagious viral disease is modelled as the dynamic progression of different classes of population with individuals interacting pairwise. This interaction follows a binary mechanism typical of kinetic theory, wherein agents aim to improve their condition with respect to a mutual utility target. To this end, we introduce kinetic equations of Boltzmann-type to describe the time evolution of the probability distributions of the multi-agent system. The interactions between agents are defined using principles from price theory, specifically employing Cobb-Douglas utility functions for binary exchange and the Edgeworth box to depict the common exchange area where utility increases for both agents. Several numerical experiments presented in the paper highlight the significance of this mechanism in driving the phenomenon toward endemicity.</p></abstract>
31
KONING, JEAN-LUC. "A REVIEW ON THE INTERACTION ISSUES IN AGENT-BASED MARKETPLACES." International Journal of Information Technology & Decision Making 01, no. 03 (2002): 457–71. http://dx.doi.org/10.1142/s0219622002000294.
Texto completoResumen
While there are already literature surveys upon agent-mediated electronic commerce applications, none have specifically tackled the issue from an interaction perspective or looked at how the control is distributed among the agents. This state-of-the-art survey focuses on how agent interactions are handled. First, it deeply looks at how methods for enforcing the actions taken by agents have been dealt with, namely protocols, negotiation and auction. Second, it defines the various types of communication languages used in multi-agent market architectures. The three main alternatives are KQML, ACL and FLBC. A comparison is then made between them and shows how much they suite their purpose. Third, this paper highlights how the current electronic commerce applications provide explicit and integrated support for complex agent interactions and present several virtual institutions where agents are engaged in multiple bilateral negotiations. Finally, it discusses some related research perspectives and identify some limitations.
32
Cui, Zhoujuan, Wenshuo Peng, Yaqiang Zhang, Yiping Duan, and Xiaoming Tao. "Spatio-Temporal-Interaction Graph Neural Networks for Multi-Agent Trajectory Prediction." Journal of Physics: Conference Series 2833, no. 1 (2024): 012010. http://dx.doi.org/10.1088/1742-6596/2833/1/012010.
Texto completoResumen
Abstract For intelligent transportation systems, accurately forecasting the future trajectories of multiple agents is pivotal. Considering the increased diversity of agents within a scene, in order to capture and model the variations in their appearance, motion status, behavioral patterns, and interrelationships, we propose a simple yet effective framework based on Spatio-Temporal-Interaction Graph Neural Networks. Specifically, a Multi-Class Agent Encoder is meticulously tailored to the specific class of each agent to distill pertinent information from their motion attributes and historical trajectories. Subsequently, a Spatio-Temporal-Interaction Graph Attention Module is constructed to productively represent and learn the complex, dynamic interactions. Finally, a Multimodal Trajectory Generation Module is customized, and a learnable diversity sampling function is introduced to map the features of each agent to a set of potential variables, so as to capture the multimodal distribution of future trajectories. Empirical evaluations on the ETH/UCY and KITTI datasets reveal that our method can efficiently improve the accuracy of trajectory prediction.
33
Skanda, Suresh, Sridhar Sudarshan, B. Raj Supreeth, Mittalkod Purmina, and V. Sukhateertha. "Prism: A Multi-Agent System for Real-Time Multi- Modal Interaction in Mobile and Web Applications." International Journal of Innovative Science and Research Technology (IJISRT) 9, no. 12 (2024): 811–17. https://doi.org/10.5281/zenodo.14546550.
Texto completoResumen
The integration of multi-agent systems in mobile and web applications has opened new horizons for real- time multi- modal interaction. This paper presents a comprehensive exploration of a multi-agent framework leveraging the Qwen2.5:3B and Gemini 1.5 Flash 8B models to provide robust, scalable, and user-centric solutions. Agents for diverse functionalities—such as Cooking, Notes, Entertainment, Travel Planning, Weather, and SecureFace—are seamlessly integrated into a unified platform to address real-world challenges. The framework emphasizes dynamic adaptability, cross- platform consistency, and enhanced user experience. We also examine the architectural considerations, implementation challenges, and future directions for ensuring the reliability and efficiency of such multi-modal systems, underscoring their potential to transform digital interactions across various domains.
34
Gautier, Anna, Bruno Lacerda, Nick Hawes, and Michael Wooldridge. "Multi-Unit Auctions for Allocating Chance-Constrained Resources." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 10 (2023): 11560–68. http://dx.doi.org/10.1609/aaai.v37i10.26366.
Texto completoResumen
Sharing scarce resources is a key challenge in multi-agent interaction, especially when individual agents are uncertain about their future consumption. We present a new auction mechanism for preallocating multi-unit resources among agents, while limiting the chance of resource violations. By planning for a chance constraint, we strike a balance between worst-case approaches, which under-utilise resources, and expected-case approaches, which lack formal guarantees. We also present an algorithm that allows agents to generate bids via multi-objective reasoning, which are then submitted to the auction. We then discuss how the auction can be extended to non-cooperative scenarios. Finally, we demonstrate empirically that our auction outperforms state-of-the-art techniques for chance-constrained multi-agent resource allocation in complex settings with up to hundreds of agents.
35
Kim, Jonghoek. "Three-Dimensional Multi-Agent Foraging Strategy Based on Local Interaction." Sensors 23, no. 19 (2023): 8050. http://dx.doi.org/10.3390/s23198050.
Texto completoResumen
This paper considers a multi-agent foraging problem, where multiple autonomous agents find resources (called pucks) in a bounded workspace and carry the found resources to a designated location, called the base. This article considers the case where autonomous agents move in unknown 3-D workspace with many obstacles. This article describes 3-D multi-agent foraging based on local interaction, which does not rely on global localization of an agent. This paper proposes a 3-D foraging strategy which has the following two steps. The first step is to detect all pucks inside the 3-D cluttered unknown workspace, such that every puck in the workspace is detected in a provably complete manner. The next step is to generate a path from the base to every puck, followed by collecting every puck to the base. Since an agent cannot use global localization, each agent depends on local interaction to bring every puck to the base. In this article, every agent on a path to a puck is used for guiding an agent to reach the puck and to bring the puck to the base. To the best of our knowledge, this article is novel in letting multiple agents perform foraging and puck carrying in 3-D cluttered unknown workspace, while not relying on global localization of an agent. In addition, the proposed search strategy is provably complete in detecting all pucks in the 3-D cluttered bounded workspace. MATLAB simulations demonstrate the outperformance of the proposed multi-agent foraging strategy in 3-D cluttered workspace.
36
Zhang, Kun, Yoichiro Maeda, and Yasutake Takahashi. "Cooperative Behavior Learning Based on Social Interaction of State Conversion and Reward Exchange Among Multi-Agents." Journal of Advanced Computational Intelligence and Intelligent Informatics 15, no. 5 (2011): 606–16. http://dx.doi.org/10.20965/jaciii.2011.p0606.
Texto completoResumen
In multi-agent systems, it is necessary for autonomous agents to interact with each other in order to have excellent cooperative performance. Therefore, we have studied social interaction between agents to see how they acquire cooperative behavior. We have found that sharing environmental states can improve agent cooperation through reinforcement learning, and that changing environmental states to target-related individual states improves cooperation. To further improve cooperation, we propose reward redistribution based on reward exchanges among agents. In receiving rewards from both the environment and other agents, agents learned how to adjust themselves to the environment and how to explore and strengthen cooperation in tasks that a single agent could not do alone. Agents thus cooperate best through the interaction of state conversion and reward exchange.
37
Seabra, Antony, Claudio Cavalcante, Joao Nepomuceno, Lucas Lago, Nicolaas Ruberg, and Sergio Lifschitz. "Orchestrating Multi-Agent Systems for Multi-Source Information Retrieval and Question Answering with Large Language Models." International Journal on Natural Language Computing 13, no. 5/6 (2024): 27–46. https://doi.org/10.5121/ijnlc.2024.13603.
Texto completoResumen
We present a novel framework for developing robust multi-source questionanswer systems by dynamically integrating Large Language Models with diverse data sources. This framework leverages a multi-agent architecture to coordinate the retrieval and synthesis of information from unstructured documents, like PDFs, and structured databases. Specialized agents, including SQL agents, Retrieval-Augmented Generation agents, and router agents, dynamically select and execute the most suitable retrieval strategies for each query. To enhance contextual relevance and accuracy, the framework employs adaptive prompt engineering, fine-tuned to the specific requirements of each interaction. We demonstrate the effectiveness of this approach in the domain of Contract Management, where answering complex queries often demands seamless collaboration between structured and unstructured data. The results highlight the framework’s capability to deliver precise, context-aware responses, establishing a scalable solution for multi-domain question-answer applications.
38
Araújo, Tanya, and Francisco Louçã. "Modeling a Multi-Agents System as a Network." International Journal of Agent Technologies and Systems 1, no. 4 (2009): 17–29. http://dx.doi.org/10.4018/jats.2009100102.
Texto completoResumen
The article presents an empirically oriented investigation on the dynamics of a specific case of a multi-agents system, the stock market. It demonstrates that S&P500 market space can be described using the geometrical and topological characteristics of its dynamics. The authors proposed to measure the coefficient R, an index providing information on the evolution of a manifold describing the dynamics of the market. It indicates the moments of perturbations, proving that the dynamics is driven by shocks and by a structural change. This dynamics has a characteristic dimension, which also allows for a description of its evolution. The consequent description of the market as a network of stocks is useful for the identification of patterns that emerge from multi-agent interaction, and defines our research, as it is derived from a system of measure and it is part of the logic of a defined mathematics.
39
Iqbal, Muhammad Munwar, Yasir Saleem, Kashif Naseer, and Mucheol Kim. "Multimedia based student-teacher smart interaction framework using multi-agents in eLearning." Multimedia Tools and Applications 77, no. 4 (2017): 5003–26. http://dx.doi.org/10.1007/s11042-017-4615-z.
Texto completo
40
Karamysheva, N. S., and S. A. Zinkin. "Interaction of cognitive and reactive agents in an intelligent computing system: operational semantics." Proceedings of the Southwest State University 28, no. 4 (2025): 138–53. https://doi.org/10.21869/2223-1560-2024-28-4-138-153.
Texto completoResumen
Purpose of research. The aim of this work is to develop an approach to constructing intelligent systems based on a replenished semantic network and a multi-agent environment with agents of various types: cognitive and deductive reactive. The architecture of a multi-level intelligent system is proposed and substantiated, which uses cognitive and reactive intelligent agents that differ in composition and number of implemented cognitive and deductive presumptions. Methods. Knowledge about the subject area is formalized both using the modal version of the first-order predicate calculus for describing cognitive agents and in terms of classical non-modal versions of predicate calculus and deductive inference mechanisms for reactive agents. The operation of an intelligent system is described by an incompletely defined semantic network represented by a conceptual graph and a system of production rules. Results. A functional architecture of an intelligent agent-based system is proposed. At the conceptual level, the architecture of an intelligent agent-based system is proposed to be represented by three sublevels. Cognitive agentsuse knowledge and beliefs that follow from epistemic logic systems. Cognitive presumptions of these agents include beliefs, goals, intentions, and desires of agents and are modeled within the framework of BDI logic. Conclusion. The conducted study shows the importance of BDI logic for cognitive agents, although it was used insignificantly in solving the task at hand, at the level of the content-conceptual description of the intelligent system. The extended functions of cognitive agents include the execution of input, registration, transmission and comparison of lists of objects and relations between them. The goals for the subsequent interpretation of cognitive agents are defined.
41
Zhao, Zhitong, Ya Zhang, Siying Wang, Yang Zhou, Ruoning Zhang, and Wenyu Chen. "Assisted-Value Factorization with Latent Interaction in Cooperate Multi-Agent Reinforcement Learning." Mathematics 13, no. 9 (2025): 1429. https://doi.org/10.3390/math13091429.
Texto completoResumen
With the development of value decomposition methods, multi-agent reinforcement learning (MARL) has made significant progress in balancing autonomous decision making with collective cooperation. However, the collaborative dynamics among agents are continuously changing. The current value decomposition methods struggle to adeptly handle these dynamic changes, thereby impairing the effectiveness of cooperative policies. In this paper, we introduce the concept of latent interaction, upon which an innovative method for generating weights is developed. The proposed method derives weights from the history information, thereby enhancing the accuracy of value estimations. Building upon this, we further propose a dynamic masking mechanism that recalibrates history information in response to the activity level of agents, improving the precision of latent interaction assessments. Experimental results demonstrate the improved training speed and superior performance of the proposed method in both a multi-agent particle environment and the StarCraft Multi-Agent Challenge.
42
Adam, Emmanuel, Martial Razakatiana, René Mandiau, and Christophe Kolski. "Matrices Based on Descriptors for Analyzing the Interactions between Agents and Humans." Information 14, no. 6 (2023): 313. http://dx.doi.org/10.3390/info14060313.
Texto completoResumen
The design of agents interacting with human beings is becoming a crucial problem in many real-life applications. Different methods have been proposed in the research areas of human–computer interaction (HCI) and multi-agent systems (MAS) to model teams of participants (agents and humans). It is then necessary to build models analyzing their decisions when interacting, while taking into account the specificities of these interactions. This paper, therefore, aimed to propose an explicit model of such interactions based on game theory, taking into account, not only environmental characteristics (e.g., criticality), but also human characteristics (e.g., workload and experience level) for the intervention (or not) of agents, to help the latter. Game theory is a well-known approach to studying such social interactions between different participants. Existing works on the construction of game matrices required different ad hoc descriptors, depending on the application studied. Moreover, they generally focused on the interactions between agents, without considering human beings in the analysis. We show that these descriptors can be classified into two categories, related to their effect on the interactions. The set of descriptors to use is thus based on an explicit combination of all interactions between agents and humans (a weighted sum of 2-player matrices). We propose a general model for the construction of game matrices based on any number of participants and descriptors. It is then possible to determine using Nash equilibria whether agents decide (or not) to intervene during the tasks concerned. The model is also evaluated through the determination of the gains obtained by the different participants. Finally, we illustrate and validate the proposed model using a typical scenario (involving two agents and two humans), while describing the corresponding equilibria.
43
Dubenko, Yu V. "AN ALGORITHM OF THE COLLECTIVE INTERACTION OF INTELLIGENT AGENTS IN CENTRALIZED MULTI-AGENT SYSTEMS." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 220 (October 2022): 30–42. http://dx.doi.org/10.14489/vkit.2022.10.pp.030-042.
Texto completoResumen
A centralized multiagent system based on the methods of feudal reinforcement learning, including agents-managers and agents-subordinates, is considered. A brief review of the author’s previous works on this topic is given. The standard algorithm for the functioning of systems of this type is considered, including the translation of the decision maker to agents-managers, the division of tasks by agents-managers into a set of subtasks, the choice by the agent-manager of the strategy used, the formation of reward functions by agents-managers, the assignment of tasks to agents-subordinates, the execution by agents-subordinates assigned tasks. The main problems of this algorithm are presented, changes are made to ensure the possibility of automatically assigning agent-managers and forming groups of subordinate agents around them, reproducing and exchanging experience. More attention is paid to the problem of experience exchange, the main ways of experience exchange are given. The principles of operation of a machine vision system that implements an upgraded algorithm are described. An assessment of the effectiveness of the obtained algorithm for the collective interaction of intelligent agents using a software model developed in Microsoft Unity is given. A comparison is made between the standard algorithm for multiagent interaction and the proposed algorithm for the collective interaction of intelligent agents in centralized multi-agent systems based on the approach of reinforcement learning and visualization of three-dimensional scenes. The conclusion is made about the expediency of using the developed algorithmt.
44
Oleksandr, Milov, Voitko Alexander, Husarova Iryna, et al. "DEVELOPMENT OF METHODOLOGY FOR MODELING THE INTERACTION OF ANTAGONISTIC AGENTS IN CYBERSECURITY SYSTEMS." Eastern-European Journal of Enterprise Technologies 2, no. 9 (98) (2019): 56–66. https://doi.org/10.15587/1729-4061.2019.164730.
Texto completoResumen
The basic concepts that form the basis of integrated modeling of the behavior of antagonistic agents in cybersecurity systems are identified. It is shown that the emphasis is largely on modeling the behavior of one of the cyber conflict parties only. In the case when the interaction of all parties to the conflict is considered, the approaches used are focused on solving particular problems, or they model a simplified situation. A methodology for modeling the interaction of antagonistic agents in cybersecurity systems, focused on the use of a multi-model complex with elements of cognitive modeling, is proposed. For this objective, the main components of cyber conflict are highlighted, the models of which must be developed. Modeling the interaction of antagonistic agents is proposed to be implemented as a simulation of situations. The concept of a situation is formulated and its components are presented. In the proposed methodology, traditional methods and modeling tools are not opposed, but are considered together, thus forming a unified methodological basis for modeling the antagonistic agents’ behavior. In the proposed multi-model complexes, the individual elements and functions of the entities under study are described using various classes of models at a certain level of detail. Coordinated use of various models allows improving the quality of modeling by compensating for the shortcomings of some models by the advantages of others, in particular, reflecting the dynamics of interaction in system-dynamic and agent-based models, which is difficult in classical models of game theory. Multi-model complexes allow stating the concept of «virtual modeling». This concept allows simulation using models of various classes. The choice of a class of models should correspond to the goals and objectives of modeling, the nature and structure of the source data. As a result of research, a methodology is proposed for modeling the interaction of antagonistic agents in cybersecurity systems using methods based on the proposed models of the reflective behavior of antagonistic agents under modern hybrid threats conditions
45
Cao, Hong, Rong Ma, Yanlong Zhai, and Jun Shen. "LLM-Collab: a framework for enhancing task planning via chain-of-thought and multi-agent collaboration." Applied Computing and Intelligence 4, no. 2 (2024): 328–48. https://doi.org/10.3934/aci.2024019.
Texto completoResumen
<p>Large language models have shown strong capabilities in performing natural language planning tasks, largely due to the chain-of-thought method, which enhances their ability to solve complex tasks through explicit intermediate inference. However, they face challenges in acquiring new knowledge, executing calculations, and interacting with the environment. Although previous work has enabled large language models to use external tools to improve reasoning and environmental interaction, there was no scalable or cohesive structure for these technologies. In this paper, we present LLM-Collab, where Collab represents the cooperative interaction between two AI agents, and the large language model plays a key role in the creation of AI agents. For this method, we took large language models as the reasoning core for AI agents and designed two AI agents to cooperate on the planning tasks: One as an analyst for tool selection and phase validation, and the other as an executor of specific tasks. Our method provided a comprehensive list of external tools to facilitate the invocation and integration of agents, ensuring a seamless collaboration process. This paradigm established a unified framework for autonomous task-solving based on massive language models by demonstrating how language communication and tool selection enable multi-agent collaboration.</p>
46
Cho, Seong-Sik, Sang-Ho Jo, Hyun-Jin Kim, et al. "Smoking may be more harmful to vasospastic angina patients who take antiplatelet agents due to the interaction: Results of Korean prospective multi-center cohort." PLOS ONE 16, no. 4 (2021): e0248386. http://dx.doi.org/10.1371/journal.pone.0248386.
Texto completoResumen
Background The interaction between smoking and the use of antiplatelet agents on the prognosis of vasospastic angina (VA) is rarely investigated. Methods VA-Korea is a nation-wide multi-center registry with prospective design (n = 1812). The primary endpoint was the composite occurrence of acute coronary syndrome (ACS), symptomatic arrhythmia, and cardiac death. Log-rank test and Cox proportional hazard model were for statistical analysis. Also, we conducted interaction analysis in both additive and multiplicative scales between smoking and antiplatelet agents among VA patients. For additive scale interaction, relative excess risk due to interaction (RERI) was calculated and for multiplicative scale interaction, the ratio of hazard ratio (HR) was calculated. All statistical analysis conducted by Stata Ver 16.1. Results Patients who were smoking and using antiplatelet agents had the highest incidence rate in the primary composite outcome. The incidence rate was 3.49 per 1,000 person-month (95% CI: 2.30-5.30, log-rank test for primary outcome p = 0.017) and HR of smoking and using antiplatelet agents was 1.66 (95%CI: 0.98-2.81). The adjusted RERI of smoking and using antiplatelet agents was 1.10 (p = 0.009), and the adjusted ratio of HR of smoking and using antiplatelet agents was 3.32 (p = 0.019). The current study observed the interaction between smoking and using antiplatelet agents in both additive and multiplicative scales. Conclusions Smoking was associated with higher rates of unfavorable clinical outcomes among VA patients taking antiplatelet agents. This suggested that VA patients, especially those using antiplatelet agents should quit smoking.
47
Бредихин, А. В., Д. В. Веркошанский, Е. О. Неретин, and О. В. Собенина. "Intercomponent interaction in a multi-agent system." МОДЕЛИРОВАНИЕ, ОПТИМИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ 11, no. 3(42) (2023): 22–23. http://dx.doi.org/10.26102/2310-6018/2023.42.3.022.
Texto completoResumen
Статья посвящена изучению механизмов межкомпонентного взаимодействия в мультиагентных системах. В работе рассмотрены различные подходы к обмену сообщениями между компонентами, а также преимущества и недостатки каждого из них. Определены ключевые проблемы межкомпонентного взаимодействия и предложены их решения. Особое внимание уделено механизму обмена сообщениями на основе брокера сообщений. В статье описаны принципы работы программного брокера, его преимущества и недостатки, а также примеры использования в мультиагентных системах. Результаты исследования показали, что использование брокера сообщений позволяет создать гибкую и масштабируемую систему, способную эффективно обрабатывать большое количество сообщений и поддерживать высокую надежность в работе. В работе представлено описание разработанной структуры формата передачи данных между компонентами мультиагентной системы. Показаны схемы маршрутизации сообщений в рамках системы с использованием брокера сообщений. Описана настройка для реализации разработанных схем межкомпонентного взаимодействия. Предложен механизм кодирования сообщений на основе тэг-ключей, который позволяет проводить их идентификацию для дальнейшей обработки программными агентами. Этот подход может быть полезен при проектировании и разработке различных мультиагентных систем, где необходим обмен сообщениями между различными программными агентами. The article examines the mechanisms of intercomponent interaction in multi-agent systems. The paper discusses various approaches to messaging between components as well as the advantages and disadvantages of each of them. The key problems of intercomponent interaction are identified and their solutions are proposed. Particular attention is paid to the messaging mechanism based on the message broker. The principles of the broker, its advantages and disadvantages as well as examples of use in multi-agent systems are described. The results of the study showed that the use of the message broker makes it possible to create a flexible and scalable system that can efficiently process a large number of messages and maintain high reliability in operation. The paper presents a description of the data transfer format structure between the components of a multi-agent system. Message routing schemes within the system using a message broker are shown. The configuration for the implementation of the intercomponent interaction schemes is described. A mechanism for encoding messages based on tag keys is proposed, which enables their identification for further processing by software agents. This approach can be useful in the design and development of various multi-agent systems, where it is necessary to exchange messages between different software agents.
48
Дубенко, Ю. В. "METHOD OF REUSE AND EXCHANGE OF EXPERIENCE IN THE COLLECTIVE INTERACTION OF INTELLIGENT AGENTS." ВЕСТНИК ВОРОНЕЖСКОГО ГОСУДАРСТВЕННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА, no. 1 (March 14, 2022): 62–72. http://dx.doi.org/10.36622/vstu.2022.18.1.007.
Texto completoResumen
Определены проблемы обмена и воспроизведения опыта, сгенерированного различными агентами, в задаче многоагентного обучения с подкреплением. Кратко рассмотрены другие работы автора статьи в области многоагентного обучения с подкреплением многоагентных систем, а также выводы из этих работ. Определено, что к числу проблем многоагентного обучения с подкреплением относятся проблемы обмена и воспроизведения опыта, сгенерированного различными агентами. Рассмотрена централизованная многоагентная система, основанная на принципах обучения с подкреплением. Описаны виды агентов, которые включает данная система: агент-менеджер, обладающий мощным аппаратным обеспечением, осуществляющий управление группой агентов в рамках реализации обучения с подкреплением для централизованных многоагентных систем, и агент-подчинённый, предназначенный для непосредственного решения практических задач. Приведён стандартный алгоритм обмена опытом между агентами. Предложены решения проблемы приоритета применения опыта, полученного при решении задач различных типов, и проблемы адаптации и применения опыта, формализованного в виде макродействий. Показано, что применение макродействий может обеспечить меньшее время достижения состояния поставленной задачи - выхода агентами из лабиринта, по сравнению со стандартными алгоритмами. Разработана компьютерная модель в среде Unity для проверки эффективности предложенного метода повторного применения имеющегося опыта решения задач, формализованного в виде макродействий, приведены результаты применения этой модели. Представлен подход к «классификации опыта» для интеллектуальных агентов, согласно которому опыт интеллектуального агента может быть разделен на две группы - «элементарный опыт» и «ситуативный опыт» I determined the problems of exchange and reproduction of experience generated by different agents in the problem of multi-agent reinforcement learning. I briefly considered my other works in the field of multi-agent reinforcement learning and multi-agent systems, as well as conclusions from these works. I determined that among the problems of multi-agent reinforcement learning are the problems of exchange and reproduction of experience generated by different agents. Here I considered a centralized multi-agent system based on the principles of reinforcement learning and described the types of agents that this system includes: an agent-manager with powerful hardware that manages a group of agents as part of the implementation of reinforcement learning for centralized multi-agent systems, and a subordinate agent designed to directly solve practical problems. I give a standard algorithm for the exchange of experience between agents and propose solutions to the problem of the priority of applying experience gained in solving problems of various types and the problem of adapting and applying experience formalized in the form of macro-actions. I show that the use of macro-actions can provide a shorter time to reach the state of the task of exiting the labyrinth by agents compared to standard algorithms. I developed a computer model in the Unity environment to test the effectiveness of the proposed method of re-applying the existing experience in solving problems, formalized in the form of macro-actions, and presented the results of applying this model and an approach to the "classification of experience" for intelligent agents, according to which the experience of an intelligent agent can be divided into two groups - "elementary experience" and "situational experience"
49
Koochakzadeh, Abbasali, Mojtaba Naderi Soorki, Aydin Azizi, Kamran Mohammadsharifi, and Mohammadreza Riazat. "Delay-Dependent Stability Region for the Distributed Coordination of Delayed Fractional-Order Multi-Agent Systems." Mathematics 11, no. 5 (2023): 1267. http://dx.doi.org/10.3390/math11051267.
Texto completoResumen
Delay and especially delay in the transmission of agents’ information, is one of the most important causes of disruption to achieving consensus in a multi-agent system. This paper deals with achieving consensus in delayed fractional-order multi-agent systems (FOMAS). The aim in the present note is to find the exact maximum allowable delay in a FOMAS with non-uniform delay, i.e., the case in which the interactions between agents are subject to non-identical communication time-delays. By proving a stability theorem, the results available for non-delayed networked fractional-order systems are extended for the case in which interaction links have nonequal communication time-delays. In this extension by considering a time-delay coordination algorithm, necessary and sufficient conditions on the time delays and interaction graph are presented to guarantee the coordination. In addition, the delay-dependent stability region is also obtained. Finally, the dependency of the maximum allowable delay on two parameters, the agent fractional-order and the largest eigenvalue of the graph Laplacian matrix, is exactly determined. Numerical simulation results are given to confirm the proposed methodologies.
50
Randhavane, Tanmay, Aniket Bera, and Dinesh Manocha. "F2FCrowds: Planning Agent Movements to Enable Face-to-Face Interactions." Presence: Teleoperators and Virtual Environments 26, no. 2 (2017): 228–46. http://dx.doi.org/10.1162/pres_a_00294.
Texto completoResumen
The simulation of human behaviors in virtual environments has many applications. In many of these applications, situations arise in which the user has a face-to-face interaction with a virtual agent. In this work, we present an approach for multi-agent navigation that facilitates a face-to-face interaction between a real user and a virtual agent that is part of a virtual crowd. In order to predict whether the real user is approaching a virtual agent to have a face-to-face interaction or not, we describe a model of approach behavior for virtual agents. We present a novel interaction velocity prediction (IVP) algorithm that is combined with human body motion synthesis constraints and facial actions to improve the behavioral realism of virtual agents. We combine these techniques with full-body virtual crowd simulation and evaluate their benefits by conducting a user study using Oculus HMD in an immersive environment. Results of this user study indicate that the virtual agents using our interaction algorithms appear more responsive and are able to elicit more reaction from the users. Our techniques thus enable face-to-face interactions between a real user and a virtual agent and improve the sense of presence observed by the user.