scholarly journals Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes

2020 ◽  
Vol 10 (17) ◽  
pp. 5828
Author(s):  
Jinbae Kim ◽  
Hyunsoo Lee
Keyword(s):  
Evaluation Framework ◽  
Learning Performance ◽  
Human Intervention ◽  
Competitive Network ◽  
Human Evaluation ◽  
Fast Training ◽  
Topology Changes ◽  
Agent Interaction ◽  
Network Topologies ◽  
Multi Agent

In recent years, the problem of reinforcement learning has become increasingly complex, and the computational demands with respect to such processes have increased. Accordingly, various methods for effective learning have been proposed. With the help of humans, the learning object can learn more accurately and quickly to maximize the reward. However, the rewards calculated by the system and via human intervention (that make up the learning environment) differ and must be used accordingly. In this paper, we propose a framework for learning the problems of competitive network topologies, wherein the environment dynamically changes agent, by computing the rewards via the system and via human evaluation. The proposed method is adaptively updated with the rewards calculated via human evaluation, making it more stable and reducing the penalty incurred while learning. It also ensures learning accuracy, including rewards generated from complex network topology consisting of multiple agents. The proposed framework contributes to fast training process using multi-agent cooperation. By implementing these methods as software programs, this study performs numerical analysis to demonstrate the effectiveness of the adaptive evaluation framework applied to the competitive network problem depicting the dynamic environmental topology changes proposed herein. As per the numerical experiments, the greater is the human intervention, the better is the learning performance with the proposed framework.

scholarly journals Adaptive Human–Machine Evaluation Framework Using Stochastic Gradient Descent-Based Reinforcement Learning for Dynamic Competing Network

2020 ◽  
Vol 10 (7) ◽  
pp. 2558 ◽  
Author(s):  
Jinbae Kim ◽  
Hyunsoo Lee
Keyword(s):  
Reinforcement Learning ◽  
Problem Solving ◽  
Special Problem ◽  
Evaluation Framework ◽  
Stochastic Gradient Descent ◽  
Human Evaluation ◽  
Basketball Game ◽  
Network Topologies ◽  
Multiple Network ◽  
Considerable Work

Complex problems require considerable work, extensive computation, and the development of effective solution methods. Recently, physical hardware- and software-based technologies have been utilized to support problem solving with computers. However, problem solving often involves human expertise and guidance. In these cases, accurate human evaluations and diagnoses must be communicated to the system, which should be done using a series of real numbers. In previous studies, only binary numbers have been used for this purpose. Hence, to achieve this objective, this paper proposes a new method of learning complex network topologies that coexist and compete in the same environment and interfere with the learning objectives of the others. Considering the special problem of reinforcement learning in an environment in which multiple network topologies coexist, we propose a policy that properly computes and updates the rewards derived from quantitative human evaluation and computes together with the rewards of the system. The rewards derived from the quantitative human evaluation are designed to be updated quickly and easily in an adaptive manner. Our new framework was applied to a basketball game for validation and demonstrated greater effectiveness than the existing methods.

scholarly journals Optimal Coordination of Over-Current Relays in Microgrids Using Unsupervised Learning Techniques

2021 ◽  
Vol 11 (3) ◽  
pp. 1241
Author(s):  
Sergio D. Saldarriaga-Zuluaga ◽  
Jesús M. López-Lezama ◽  
Nicolás Muñoz-Galeano
Keyword(s):  
Unsupervised Learning ◽  
Distributed Generation ◽  
Network Topology ◽  
International Electrotechnical Commission ◽  
Number Of Clusters ◽  
Learning Techniques ◽  
Topology Changes ◽  
Network Topologies ◽  
Optimal Coordination ◽  
Operational Modes

Microgrids constitute complex systems that integrate distributed generation (DG) and feature different operational modes. The optimal coordination of directional over-current relays (DOCRs) in microgrids is a challenging task, especially if topology changes are taken into account. This paper proposes an adaptive protection approach that takes advantage of multiple setting groups that are available in commercial DOCRs to account for network topology changes in microgrids. Because the number of possible topologies is greater than the available setting groups, unsupervised learning techniques are explored to classify network topologies into a number of clusters that is equal to the number of setting groups. Subsequently, optimal settings are calculated for every topology cluster. Every setting is saved in the DOCRs as a different setting group that would be activated when a corresponding topology takes place. Several tests are performed on a benchmark IEC (International Electrotechnical Commission) microgrid, evidencing the applicability of the proposed approach.

scholarly journals A Novel Multi-Agent Model for Robustness with Component Failure and Malware Propagation in Wireless Sensor Networks

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4873
Author(s):  
Biao Xu ◽  
Minyan Lu ◽  
Hong Zhang ◽  
Cong Pan
Keyword(s):  
Wireless Sensor ◽  
Component Reliability ◽  
Agent Based ◽  
Agent Model ◽  
Cross Domain ◽  
Malware Propagation ◽  
Network Topologies ◽  
Multi Agent ◽  
Agent Characteristics ◽  
Information Domain

A wireless sensor network (WSN) is a group of sensors connected with a wireless communications infrastructure designed to monitor and send collected data to the primary server. The WSN is the cornerstone of the Internet of Things (IoT) and Industry 4.0. Robustness is an essential characteristic of WSN that enables reliable functionalities to end customers. However, existing approaches primarily focus on component reliability and malware propagation, while the robustness and security of cascading failures between the physical domain and the information domain are usually ignored. This paper proposes a cross-domain agent-based model to analyze the connectivity robustness of a system in the malware propagation process. The agent characteristics and transition rules are also described in detail. To verify the practicality of the model, three scenarios based on different network topologies are proposed. Finally, the robustness of the scenarios and the topologies are discussed.

UUV formation system modeling and simulation research based on Multi-Agent Interaction Chain

2015 ◽  
Vol 06 (02) ◽  
pp. 1550019 ◽  
Author(s):  
Hongtao Liang ◽  
Fengju Kang ◽  
Honghong Li
Keyword(s):  
Modeling And Simulation ◽  
System Modeling ◽  
Rule Base ◽  
Communication Model ◽  
Static Structure ◽  
Dynamic Contract ◽  
Novel Approach ◽  
Agent Interaction ◽  
Multi Agent ◽  
Formation System

Unmanned Underwater Vehicle (UUV) formation system has an important role in the utilization of marine resource. In order to provide an efficient method to research modeling and simulation of UUV formation in the marine environment, the novel approach based on Multi-Agent Interaction Chain was proposed for the UUV formation system. Firstly, Multi-Agent Interaction Chain was analyzed, which mainly considered task and role of UUV in the formation, and the overall modeling process of UUV formation system based on Multi-Agent Interaction Chain was established. Then, the static structure of Multi-Agent Interaction Chain was researched focusing on Hybrid UUV-Agent model structure from the UUV-Agent State-Set and UUV-Agent Rule-Base which were the two aspects to strengthen reliability of interaction chain; the dynamic mechanism of Multi-Agent Interaction Chain was designed, which was focused on collaboration model and communication model through the Adaptive Dynamic Contract Net Protocol and KQML/XML/RTI. Finally, three experiments were established to verify the validity and effectiveness of proposed modeling approach for UUV formation system. Simulation results show the proposed model has good performance, which has important theoretical innovation and application prospects.

Hybrid Emotionally Aware Mediated Multiagency

2012 ◽  
pp. 1314-1329
Author(s):  
Giovanni Vincenti ◽  
James Braman
Keyword(s):  
Artificial Intelligence ◽  
Artificial Life ◽  
Consumer Products ◽  
Agent Societies ◽  
Everyday Lives ◽  
Agent Interaction ◽  
Multi Agent ◽  
Thinking Processes

Emotions influence our everyday lives, guiding and misguiding us. They lead us to happiness and love, but also to irrational acts. Artificial intelligence aims at constructing agents that can emulate thinking processes, but artificial life still lacks emotions and all the consequences that come from them. This work introduces an emotionally aware framework geared towards multi-agent societies. Basing our model on the shoulders of solid foundations created by pioneers who first explored the coupling of emotions and agency, we extend their ideas to include inter-agent interaction and virtual genetics as key components of an agent’s emotive state. We also introduce possible future applications of this framework in consumer products as well as research endeavors.

Semantic Interoperability of Geospatial Services

2010 ◽  
pp. 400-421
Author(s):  
Iftikhar U. Sikder ◽  
Santosh K. Misra
Keyword(s):  
Spatial Reasoning ◽  
Spatial Information ◽  
Resource Integration ◽  
Semantic Level ◽  
Collaborative Modeling ◽  
Multiple Data ◽  
Agent Interaction ◽  
Agent Collaboration ◽  
Multi Agent ◽  
Geospatial Services

This article proposes a multi-agent based framework that allows multiple data sources and models to be semantically integrated for spatial modeling in business processing. The paper reviews the feasibility of ontology-based spatial resource integration options to combine the core spatial reasoning with domainspecific application models. We propose an ontology-based framework for semantic level communication of spatial objects and application models. We then introduce a multi-agent system, ontology-based spatial information and resource integration services (OSIRIS), to semantically interoperate complex spatial services and integrate them in a meaningful composition. The advantage of using multi-agent collaboration in OSIRIS is that it obviates the need for end-user analysts to be able to decompose a problem domain to subproblems or to map different models according to what they actually mean. We also illustrate a multi-agent interaction scenario for collaborative modeling of spatial applications using the proposed custom feature of OSIRIS.

On distributed artificial intelligence

1988 ◽  
Vol 3 (1) ◽  
pp. 21-57 ◽  
Author(s):  
Luis Eduardo ◽  
Castillo Hern
Keyword(s):  
Artificial Intelligence ◽  
Conceptual Model ◽  
Intelligent Agents ◽  
Distributed Artificial Intelligence ◽  
Agent Interaction ◽  
Multi Agent

AbstractDistributed Artificial Intelligence has been loosely defined in terms of computation by distributed, intelligent agents. Although a variety of projects employing widely ranging methodologies have been reported, work in the field has matured enough to reveal some consensus about its main characteristics and principles. A number of prominent projects are described in detail, and two general frameworks, theSystem conceptual modeland theagent conceptual model, are used to compare the different approaches. The paper concludes by reviewing approaches to formalizing some of the more critical capabilities required by multi-agent interaction.

Sign in / Sign up

Export Citation Format

Share Document