scholarly journals Improving Multi-agent Coordination by Learning to Estimate Contention

2021 ◽  
Author(s):  
Panayiotis Danassis ◽  
Florian Wiedemair ◽  
Boi Faltings
Keyword(s):  
Large Scale ◽  
Learning Algorithm ◽  
Coordination Mechanism ◽  
Large Scale Systems ◽  
Fast Learning ◽  
Agent Learning ◽  
Meeting Scheduling ◽  
Multi Agent ◽  
Device Deployment ◽  
Agent Coordination

We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems. We circumvent the traditional pitfalls of multi-agent learning (e.g., the moving target problem, the curse of dimensionality, or the need for mutually consistent actions) by relying on the ALMA heuristic as a coordination mechanism for each stage game. ALMA-Learning is decentralized, observes only own action/reward pairs, requires no inter-agent communication, and achieves near-optimal (<5% loss) and fair coordination in a variety of synthetic scenarios and a real-world meeting scheduling problem. The lightweight nature and fast learning constitute ALMA-Learning ideal for on-device deployment.

Incremental Distributed Learning with JavaScript Agents for Earthquake and Disaster Monitoring

2017 ◽  
Vol 8 (4) ◽  
pp. 34-53 ◽  
Author(s):  
Stefan Bosse
Keyword(s):  
Mobile Agents ◽  
Large Scale ◽  
Learning Algorithm ◽  
Seismic Station ◽  
Geodetic Network ◽  
Distributed Learning ◽  
The Internet ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Multi Agent

Ubiquitous computing and The Internet-of-Things (IoT) grow rapidly in today's life and evolving to Self-organizing systems (SoS). A unified and scalable information processing and communication methodology is required. In this work, mobile agents are used to merge the IoT with Mobile and Cloud environments seamless. A portable and scalable Agent Processing Platform (APP) provides an enabling technology that is central for the deployment of Multi-Agent Systems (MAS) in strong heterogeneous networks including the Internet. A large-scale use-case deploying Multi-agent systems in a distributed heterogeneous seismic sensor and geodetic network is used to demonstrate the suitability of the MAS and platform approach. The MAS is used for earthquake monitoring based on a new incremental distributed learning algorithm applied to seismic station data, which can be extended by ubiquitous sensing devices like smart phones. Different (mobile) agents perform sensor sensing, aggregation, local learning and prediction, global voting and decision making, and the application.

scholarly journals Research on the coordination mechanism of major industrial project engineering and construction multi-agents based on structural holes theory

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0255858
Author(s):  
Xiaokang Han ◽  
Wenzhou Yan ◽  
Mei Lu
Keyword(s):  
Complex Network ◽  
Coordination Mechanism ◽  
Coordination Problem ◽  
Structural Holes ◽  
Network Diagram ◽  
Pmc Model ◽  
3D Network ◽  
Industrial Projects ◽  
Multi Agent ◽  
Agent Coordination

Industry is an important pillar of the national economy. Industrial projects are the most complex and difficult projects to control in the construction industry, and major industrial projects are even more complex and difficult to control. Multi-agent coordination is one of the core issues of industrial projects. Based on an analysis of the engineering and construction chains and agent relationships and agent networks of industrial projects, a complex network of the engineering and construction agents of industrial projects is established, and the complex network structural holes theory is applied to study the nonrepeated relationships among agents in industrial projects. Assuming agents are linked through contract relations and the most critical contract index between the agents in the contract amount, through structural hole analysis considering the EPC and PMC model, the aggregate constraint list is obtained, 2D network diagram and 3D network diagram are shown. According to the aggregate constraint value, the EPC contractor with the minimum aggregate constraint value and the project management company with the minimum aggregate constraint value are the critical agent in EPC and PMC model. By analyzing the complex network comprising different models of industrial projects, it is concluded that the characteristics of the agent maintain an advantage in competition, the coordination mechanism of the integration of agent interests, and multi-agent relations are considered to solve the multi-agent coordination problem in major industrial projects.

scholarly journals Neural Regret-Matching for Distributed Constraint Optimization Problems

2021 ◽  
Author(s):  
Yanchen Deng ◽  
Runsheng Yu ◽  
Xinrun Wang ◽  
Bo An
Keyword(s):  
Large Scale ◽  
Optimization Problems ◽  
Scale Up ◽  
Constraint Optimization ◽  
Confidence Bounds ◽  
Distributed Constraint Optimization ◽  
Multi Agent ◽  
Constraint Optimization Problems ◽  
Regret Bound ◽  
Agent Coordination

Distributed constraint optimization problems (DCOPs) are a powerful model for multi-agent coordination and optimization, where information and controls are distributed among multiple agents by nature. Sampling-based algorithms are important incomplete techniques for solving medium-scale DCOPs. However, they use tables to exactly store all the information (e.g., costs, confidence bounds) to facilitate sampling, which limits their scalability. This paper tackles the limitation by incorporating deep neural networks in solving DCOPs for the first time and presents a neural-based sampling scheme built upon regret-matching. In the algorithm, each agent trains a neural network to approximate the regret related to its local problem and performs sampling according to the estimated regret. Furthermore, to ensure exploration we propose a regret rounding scheme that rounds small regret values to positive numbers. We theoretically show the regret bound of our algorithm and extensive evaluations indicate that our algorithm can scale up to large-scale DCOPs and significantly outperform the state-of-the-art methods.

Incremental Distributed Learning With JavaScript Agents for Earthquake and Disaster Monitoring

2019 ◽  
pp. 813-833
Author(s):  
Stefan Bosse
Keyword(s):  
Mobile Agents ◽  
Large Scale ◽  
Learning Algorithm ◽  
Seismic Station ◽  
Geodetic Network ◽  
Distributed Learning ◽  
The Internet ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Multi Agent

Ubiquitous computing and The Internet-of-Things (IoT) grow rapidly in today's life and evolving to Self-organizing systems (SoS). A unified and scalable information processing and communication methodology is required. In this work, mobile agents are used to merge the IoT with Mobile and Cloud environments seamless. A portable and scalable Agent Processing Platform (APP) provides an enabling technology that is central for the deployment of Multi-Agent Systems (MAS) in strong heterogeneous networks including the Internet. A large-scale use-case deploying Multi-agent systems in a distributed heterogeneous seismic sensor and geodetic network is used to demonstrate the suitability of the MAS and platform approach. The MAS is used for earthquake monitoring based on a new incremental distributed learning algorithm applied to seismic station data, which can be extended by ubiquitous sensing devices like smart phones. Different (mobile) agents perform sensor sensing, aggregation, local learning and prediction, global voting and decision making, and the application.

Multi-Agent Applied Research in Agile Supply Chain

2013 ◽  
Vol 712-715 ◽  
pp. 3059-3062
Author(s):  
Jin Peng Tang ◽  
Ling Lin Li
Keyword(s):  
Supply Chain ◽  
System Reliability ◽  
Intelligent Agents ◽  
Applied Research ◽  
Coordination Mechanism ◽  
Supply Chain System ◽  
Agile Supply Chain ◽  
Multi Agent ◽  
Agent Coordination ◽  
The Competitiveness Of Enterprises

Introduced intelligent agents to agile supply chain, designed multi-agent coordination mechanism for agents, then proposed agile supply chain based on multi-agent system. This mechanism is applied to a specific enterprise. Multi-Agent strengthens the agile supply chain system reliability, flexibility and scalability, and improves the competitiveness of enterprises.

Decentralized control for large scale systems with inherently coupled subsystems

2021 ◽  
pp. 107754632110349
Author(s):  
Filip Svoboda ◽  
Kristian Hengster-Movric ◽  
Martin Hromčík
Keyword(s):  
Design Methodology ◽  
Large Scale ◽  
Single Agent ◽  
Control Design ◽  
Linear Matrix ◽  
Multi Agent Systems ◽  
Large Scale Systems ◽  
Coupled Subsystems ◽  
Multi Agent ◽  
Interaction Topology

This paper brings a novel scalable control design methodology for Large-Scale Systems. Such systems are considered as multi-agent systems with inherent interactions between neighboring agents. The presented design methodology uses single-agent dynamics and their interaction topology, rather than relying on the model of the entire system. The dimension of the design problem therefore remains the same with growing number of agents. This allows a feasible control design even for large systems. Moreover, the proposed design is based on simple Linear Matrix Inequalities, efficiently solvable using standard computational tools. Numerical results validate the proposed approach.

Big Data Analytics for Train Delay Prediction

2018 ◽  
pp. 320-348 ◽  
Author(s):  
Emanuele Fumeo ◽  
Luca Oneto ◽  
Giorgio Clerico ◽  
Renzo Canepa ◽  
Federico Papa ◽  
...  
Keyword(s):  
Big Data ◽  
Large Scale ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Fast Learning ◽  
Current State ◽  
Big Data Technologies ◽  
Large Scale Data Processing ◽  
Prediction Systems ◽  
Delay Prediction

Current Train Delay Prediction Systems (TDPSs) do not take advantage of state-of-the-art tools and techniques for extracting useful insights from large amounts of historical data collected by the railway information systems. Instead, these systems rely on static rules, based on classical univariate statistic, built by experts of the railway infrastructure. The purpose of this book chapter is to build a data-driven TDPS for large-scale railway networks, which exploits the most recent big data technologies, learning algorithms, and statistical tools. In particular, we propose a fast learning algorithm for Shallow and Deep Extreme Learning Machines that fully exploits the recent in-memory large-scale data processing technologies for predicting train delays. Proposal has been compared with the current state-of-the-art TDPSs. Results on real world data coming from the Italian railway network show that our proposal is able to improve over the current state-of-the-art TDPSs.

Cooperative Federated Multi-Agent Control of Large-Scale Systems

2011 ◽  
Author(s):  
Qing Dong ◽  
Kristen Bradshaw ◽  
Frank Ferrese ◽  
Li Bai ◽  
Saroj Biswas
Keyword(s):  
Large Scale ◽  
Large Scale Systems ◽  
Multi Agent ◽  
Agent Control
Sign in / Sign up

Export Citation Format

Share Document