scholarly journals Collective Online Learning of Gaussian Processes in Massive Multi-Agent Systems

2019 ◽  
Vol 33 ◽  
pp. 7850-7857 ◽  
Author(s):  
Trong Nghia Hoang ◽  
Quang Minh Hoang ◽  
Kian Hsiang Low ◽  
Jonathan How
Keyword(s):  
Online Learning ◽  
Gaussian Processes ◽  
Message Passing ◽  
Transmission Loss ◽  
Streaming Data ◽  
Multi Agent Systems ◽  
Model Fusion ◽  
Agent Model ◽  
Massive Number ◽  
Multi Agent

This paper presents a novel Collective Online Learning of Gaussian Processes (COOL-GP) framework for enabling a massive number of GP inference agents to simultaneously perform (a) efficient online updates of their GP models using their local streaming data with varying correlation structures and (b) decentralized fusion of their resulting online GP models with different learned hyperparameter settings and inducing inputs. To realize this, we exploit the notion of a common encoding structure to encapsulate the local streaming data gathered by any GP inference agent into summary statistics based on our proposed representation, which is amenable to both an efficient online update via an importance sampling trick as well as multi-agent model fusion via decentralized message passing that can exploit sparse connectivity among agents for improving efficiency and enhance the robustness of our framework against transmission loss. We provide a rigorous theoretical analysis of the approximation loss arising from our proposed representation to achieve efficient online updates and model fusion. Empirical evaluations show that COOL-GP is highly effective in model fusion, resilient to information disparity between agents, robust to transmission loss, and can scale to thousands of agents.

scholarly journals DELIBERATIVE EVOLUTION IN MULTI-AGENT SYSTEMS

2001 ◽  
Vol 11 (05) ◽  
pp. 559-581 ◽  
Author(s):  
F. M. T. BRAZIER ◽  
C. M. JONKER ◽  
J. TREUR ◽  
N. J. E. WIJNGAARDS
Keyword(s):  
Multi Agent Systems ◽  
Agent Architecture ◽  
Individual Agent ◽  
New Agents ◽  
Agent Model ◽  
Development Method ◽  
Agent Systems ◽  
Generic Agent ◽  
Multi Agent ◽  
Material Process

Evolution of automated systems, in particular evolution of automated agents based on agent deliberation, is the topic of this paper. Evolution is not a merely material process, it requires interaction within and between individuals, their environments and societies of agents. An architecture for an individual agent capable of (1) deliberation about the creation of new agents, and (2) (run-time) creation of a new agent on the basis of this, is presented. The agent architecture is based on an existing generic agent model, and includes explicit formal conceptual representations of both design structures of agents and (behavioural) properties of agents. The process of deliberation is based on an existing generic reasoning model of design. The architecture has been designed using the compositional development method DESIRE, and has been tested in a prototype implementation.

scholarly journals Fairness in multi-agent systems

2008 ◽  
Vol 23 (2) ◽  
pp. 153-180 ◽  
Author(s):  
STEVEN DE JONG ◽  
KARL TUYLS ◽  
KATJA VERBEECK
Keyword(s):  
Behavioral Economics ◽  
Computational Models ◽  
Computer Software ◽  
Multi Agent Systems ◽  
Agent Model ◽  
Agent Systems ◽  
Multi Agent ◽  
Classical Game ◽  
Descriptive Models ◽  
Classical Game Theory

AbstractMulti-agent systems are complex systems in which multiple autonomous entities, called agents, cooperate in order to achieve a common or personal goal. These entities may be computer software, robots, and also humans. In fact, many multi-agent systems are intended to operate in cooperation with or as a service for humans. Typically, multi-agent systems are designed assuming perfectly rational, self-interested agents, according to the principles of classical game theory. Recently, such strong assumptions have been relaxed in various ways. One such way is explicitly including principles derived from human behavior. For instance, research in the field of behavioral economics shows that humans are not purely self-interested. In addition, they strongly care aboutfairness. Therefore, multi-agent systems that fail to take fairness into account, may not be sufficiently aligned with human expectations and may not reach intended goals. In this paper, we present an overview of work in the area of fairness in multi-agent systems. More precisely, we first look at the classical agent model, that is, rational decision making. We then provide an outline of descriptive models of fairness, that is, models that explain how and why humans reach fair decisions. Then, we look at prescriptive, computational models for achieving fairness in adaptive multi-agent systems. We show that results obtained by these models are compatible with experimental and analytical results obtained in the field of behavioral economics.

AN AGENT BASED LANGUAGE FOR THE DEVELOPMENT OF DISTRIBUTED SOFTWARE SYSTEMS

1996 ◽  
Vol 05 (03) ◽  
pp. 347-366
Author(s):  
AGOSTINO POGGI ◽  
PAOLA TURCI
Keyword(s):  
Message Passing ◽  
Object Oriented ◽  
Software Systems ◽  
Multi Agent Systems ◽  
Agent Architecture ◽  
Distributed Software ◽  
Agent Architectures ◽  
Agent Based ◽  
Multi Agent ◽  
High Level

This paper presents a concurrent object-oriented language, called CUBL, that seems be suitable for the development and maintenance of multi-agent systems. This language is based on objects, called c_units, that act in parallel and communicate with each other through synchronous and asynchronous message passing, and allows the distribution of a program, that is, of its objects on a network of UNIX workstations. This language has been enriched with an agent architecture that offers some of more important features for agent-oriented programming and some advantages as regards the other implemented agent architectures. In particular this architecture allows the development of systems where agents communicate with each other through a high level agent communication language and can change their behavior during their life.

The Agent-Oriented Methodology MAS-CommonKADS

2011 ◽  
pp. 445-468 ◽  
Author(s):  
Carlos A. Iglesias ◽  
Mercedes Garijo
Keyword(s):  
Knowledge Engineering ◽  
Object Oriented ◽  
Design Model ◽  
Communication Model ◽  
Multi Agent Systems ◽  
Agent Model ◽  
Agent Systems ◽  
Coordination Model ◽  
Multi Agent ◽  
Generic Component

This chapter introduces the main concepts of the methodology MAS-CommonKADS that extends object-oriented and knowledge engineering techniques for the conceptualisation of multi-agent systems. MAS-CommonKADS defines a set of models (Agent Model, Task Model, Expertise Model, Coordination Model, Communication Model, Organisation Model, and Design Model) that together provide a model of the problem to be solved. Each of the components of the model is a generic component for the sake of reusability. Readers familiar with object-oriented analysis will find it easy to apply most of the techniques of MAS-CommonKADS in the development of multi-agent systems and will be introduced to the application of knowledge engineering techniques for specifying the knowledge of the agents.

scholarly journals Aspect-Oriented Approach to Implement Message Handler in Multi-agent Systems

2011 ◽  
Vol 44 (1) ◽  
pp. 38-47
Author(s):  
Aleksis Liekna ◽  
Jānis Grundspeņķis
Keyword(s):  
Knowledge Base ◽  
Multi Agent Systems ◽  
Aspect Oriented Programming ◽  
Agent Model ◽  
Agent Systems ◽  
Multi Agent ◽  
Oriented Approach

Aspect-Oriented Approach to Implement Message Handler in Multi-agent SystemsThis paper focuses on message handling in multi-agent systems. The proposed approach uses aspect-oriented programming to separate message handling from other agent concerns, thus increasing system's modularity and simplifying modification and expansion. To illustrate the proposed approach in practice, a prototype of a simple knowledge base agent model is implemented. The prototype is built on top of JADE platform. AspectJ is used for aspect-oriented implementation.

Sign in / Sign up

Export Citation Format

Share Document