Intelligent Adaptive Information Agents

Adaptation in open, multi-agent information gathering systems isimportant for several reasons. These reasons include the inability toaccurately predict future problem-solving workloads, future changes inexisting information requests, future failures and additions of agents anddata supply resources, and other future task environment characteristicchanges that require system reorganization. We have developed a multi-agentdistributed system infrastructure, RETSINA (REusable Task Structure-based Intelligent Network Agents) that handles adaptation in an open Internetenvironment. Adaptation occurs both at the individual agent level as well asat the overall agent organization level. The RETSINA system has three typesof agents. Interface agents interact with the userreceiving user specifications and delivering results. They acquire, model,and utilize user preferences to guide system coordination in support of theusers tasks. Task agents help users perform tasks byformulating problem solving plans and carrying out these plans throughquerying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneouscollection of information sources. In this paper, we concentrate on theadaptive architecture of the information agents. We use as the domain ofapplication WARREN, a multi-agent financial portfolio management system thatwe have implemented within the RETSINA framework.     

Individual learning of coordination knowledge

Abstract. Social agents, both human and computational, inhabiting a world containing multiple active agents, need to coordinate their activities. This is because agents share resources, and without proper coordination or ‘rules of the road’, everybody will be interfering with the plans of others. As such, we need coordination schemes that allow agents to effectively achieve local goals without adversely affecting the problem-solving capabilities of other agents. Researchers in the field of Distributed Artificial Intelligence (DAI) have developed a variety of coordination schemes under different assumptions about agent capabilities and relationships. Whereas some of these researchers have been motivated by human cognitive biases, others have approached it as an engineering problem of designing the most effective coordination architecture or protocol. We evaluate individual and concurrent learning by multiple, autonomous agents as a means for acquiring coordination knowledge. We show that a uniform reinforcement learning algorithm suffices as a coordination mechanism in both cooperative and adversarial situations. Using a number of multi-agent learning scenarios with both tight and loose coupling between agents and with immediate as well as delayed feedback, we demonstrate that agents can consistently develop effective policies to coordinate their actions without explicit information sharing. We demonstrate the viabilityof using both the Q-learning algorithm and genetic algorithm based classifier systems with different pay-off schemes, namely the bucket brigade algorithm (BBA) and the profit sharing plan (PSP), for developing agent coordination on two different multi-agent domains. In addition, we show that a semi-random scheme for action selection is preferable to the more traditional fitness proportionate selection scheme used in classifier systems.     

Infrastructure for Design, Deployment and Experimentation of Distributed Agent-based Systems: The Requirements, The Technologies, and An Example

This paper discusses infrastructure for design, development, and experimentation of multi-agent systems. Multi-agent system design requires determining (1) how domain requirements drive the use of agents and AI techniques, (2) what competencies agents need in a MAS, and (3) which techniques implement those competencies. Deployment requirements include code reuse, parallel development through formal standardized object specifications, multi-language and multi-platform support, simulation and experimentation facilities, and user interfaces to view internal module, agent, and system operations. We discuss how standard infrastructure technologies such as OMG IDL, OMG CORBA, Java, and VRML support these services. Empirical evaluation of complex software systems requires iteration through combinations of experimental parameters and recording desired data. Infrastructure software can ease the setup, running, and analysis of large-scale computational experiments. The development of the Sensible Agent Testbed and architecture over the past six years provides a concrete example. The design rationale for the Sensible Agent architecture emphasizes domain-independent requirements and rapid deployment to new application domains. The Sensible Agent Testbed is a suite of tools providing or assisting in setting up, running, visually monitoring, and chronicling empirical testing and operation of complex, distributed multi-agent systems. A thorough look at the various Sensible Agents infrastructure pieces illustrates the engineering principles essential for multi-agent infrastructure, while documenting the software for users.     

MVC模式在JADE系统开发中的应用

针对由于JADE(Java Agent Development Environment)对带图形界面的代理的支持程度不够,从而造成开发出来的系统结构混乱,维护困难等问题,采用MVC(Model-View-Control)设计模式进行开发,提出了一种新的图形界面Agent开发架构,即采用模型、界面和控制等功能模块相分离的方式来构造系统,以实现对多代理系统开发和维护的简化。该架构除了加强JADE系统对图形界面代理的支持外,新增了对多种消息并行处理的支持;并且结构灵活,易于扩展,可对现有的多代理系统进行少量改造来实现结构调整。     

Communication infrastructure in distributed scheduling

The emergence of distributed artificial intelligent (DAI) introduced a new approach to solve scheduling problems by a set of scheduling systems that interact with each other in the problem-solving process. In this paper, we describe a communication infrastructure to handle connection and communication between distributed Internet scheduling systems for distributed applications. First, we present an agent model of distributed scheduling systems where agents can communicate and coordinate activities with each other via an agent communication language. Then, we define the syntax and semantics for the agent communication languages, and negotiation mechanism. Following that, we discuss the design and development of the prototype for the multi-agent scheduling systems. We conclude with a discussion of communication issues for heterogeneous agent-based scheduling systems to solve distributed scheduling problems.     

ADK: An Agent Development Kit Based on a Formal Design Model for Multi-Agent Systems

The advent of multi-agent systems has brought us opportunities for the development of complex software that will serve as the infrastructure for advanced distributed applications. During the past decade, there have been many agent architectures proposed for implementing agent-based systems, and also a few efforts to formally specify agent behaviors. However, research on narrowing the gap between agent formal models and agent implementation is rare. In this paper, we propose a model-based approach to designing and implementing intelligent agents for multi-agent systems (MAS). Instead of using formal methods for the purpose of specifying agent behavior, we bring formal methods into the design phase of the agent development life cycle. Specifically, we use the formalism called agent-oriented G-net model, which is based on the G-net formalism (a type of high-level Petri net), to serve as the high-level design for intelligent agents. Based on the high-level design, we further derived the agent architecture and the detailed design for agent implementation. To demonstrate the feasibility of our approach, we developed the toolkit called ADK (Agent Development Kit) that supports rapid development of intelligent agents for multi-agent systems and we discuss the role of inheritance in agent-oriented development. As a potential solution for automated software development, we summarize the procedure to generate a model-based design of application-specific agents. Finally, to illustrate an application built on ADK, we present an air-ticket trading example.     

Flexible coordinator design for modeling resource sharing in multi-agent systems

One approach to modeling multi-agent systems (MASs) is to employ a method that defines components which describe the local behavior of individual agents, as well as a special component, called a coordinator. The coordinator component coordinates the resource sharing behavior among the agents. The agent models define a set of local plans, and the combination of local plans and a coordinator defines a system’s global plan. Although earlier work has provided the base functionality needed to synthesize inter-agent resource sharing behavior for a global, conflict-free MAS environment, the lack of coordination flexibility limits the modeling capability at both the local plan level and the global plan level. In this paper, we describe a flexible design method that supports a range of coordinator components. The method defines four levels of coordination and an associated four-step coordinator generation process, which allows for the design of coordinators with increasing capabilities for handling complexity associated with resource coordination. Colored Petri net based simulation is used to analyze various properties that derive from different coordinators and synthesis of a reduced coordinator component is discussed for cases that involve homogeneous agents.     

Learning in multi-agent systems: a case study of construction claims negotiation

The ability of agents to learn is of growing importance in multi-agent systems. It is considered essential to improve the quality of peer to peer negotiation in these systems. This paper reviews various aspects of agent learning, and presents the particular learning approach—Bayesian learning—adopted in the MASCOT system (multi-agent system for construction claims negotiation). The core objective of the MASCOT system is to facilitate construction claims negotiation among different project participants. Agent learning is an integral part of the negotiation mechanism. The paper demonstrates that the ability to learn greatly enhances agents' negotiation power, and speeds up the rate of convergence between agents. In this case, learning is essential for the success of peer to peer agent negotiation systems.     

AGENT COORDINATION CONTEXTS IN A MAS COORDINATION INFRASTRUCTURE

In order to harness complexity in multi-agent systems (MAS), first-class entities that mediate interaction between agents and environment are required, which can encapsulate control over MAS behavior and evolution. To this end, MAS infrastructures should provide mediating artifacts, both enabling and constraining agent interactions, and possibly representing admissible agent perceptions and actions over the environment.

Along this line, in this paper, we take the notion of agent coordination context (ACC) as a means to model agent-environment interactions, and show how it can be embedded within a MAS infrastructure in terms of model and runtime structures. Then, we take the TuCSoN coordination infrastructure as a reference, and extend it with the ACC abstraction to integrate the support for coordination with organization and security.     

Reactive multi-agent system for assembly cell control

This paper presents a multi-agent system for the control of manufacturing systems. The multi-agent system is designed to provide manufacturing control with three important characteristics: high robustness, quick response and good expandability. A prototype multi-agent-based control system has been developed for a flexible assembly cell as an example. The prototype multi-agent system contains several reactive agents. Each agent acts according to its built-in behaviours, and the behaviours are able to respond to stimuli from the manufacturing environment. A system architecture to implement the multi-agent-based control system is proposed and the coordination model of the reactive agents is developed. The generic agent structure is established for individual reactive agents, and the behaviours and the subsumption architecture of each agent are designed.     

e-Automation,an architecture for distributed industrial automation systems

Due to the complexity of modern industrial systems, a conventional automation system is not capable of providing sufficient information management and high-level intelligent approaches, as achieving these functionalities requires the support of comprehensive data management and coordination between system devices and heterogenous information. This paper proposes the concept of e-Automation, in which computer networking and distributed intelligence agent technologies are applied to industrial automation systems, and presents a hardware and software architecture that implements this concept. An open infrastructure based on multi-agent systems is employed in the proposed architecture of e-Automation, which aims to allow the implementation of diverse tasks and to permit greater configurability than can be obtained from a traditional system. To evaluate our proposed e-Automation concept, this paper presents a case study of substation information management which adopts the proposed e-Automation architecture in power system domain.     

Using Domain-Independent Exception Handling Services to Enable Robust Open Multi-Agent Systems: The Case of Agent Death

This paper addresses a simple but critical question: how can we create robust multi-agent systems out of the often unreliable agents and infrastructures we can expect to find in open systems contexts? We propose an approach to this problem based on distinct exception handling (EH) services that enact coordination protocol-specific but domain-independent strategies to monitor agent systems for problems (‘exceptions’) and intervene when necessary to avoid or resolve them. The value of this approach is demonstrated for the ‘agent death’ exception in the Contract Net protocol; we show through simulation that the EH service approach provides substantially improved performance compared to existing approaches in a way that is appropriate for open multi-agent systems.     

A Security Architecture for Mobile Agent Based Applications

This paper describes a security architecture for mobile agent based systems. It defines the notion of a security-enhanced agent and outlines security management components in agent platform bases and considers secure migration of agents from one base to another. The security enhanced agent carries a passport that contains its security credentials and some related security code. Then we describe how authentication, integrity and confidentiality, and access control are achieved using the agent's passport and the security infrastructure in the agent bases. We then discuss the application of the security model in roaming mobile agents and consider the types of access control policies that can be specified using the security enhanced agents and the policy base in the agent platforms. Finally we describe the security infrastructure that implements the proposed security services and outline the development of a secure agent based application using the proposed architecture.     

Enabling run-time composition and support for heterogeneous pervasive multi-agent systems

User needs-driven and computer-supported development of pervasive heterogeneous and dynamic multi-agent systems remains a great challenge for agent research community. This paper presents an innovative approach to composing, validating and supporting multi-agent systems at run-time. Multi-agent systems (MASs) can and should be assembled quasi-automatically and dynamically based on high-level user specifications which are transformed into a shared and common goal–mission. Dynamically generating agents could also be supported as a pervasive service. Heterogeneity of MASs refers to diverse functionality and constituency of the system which include mobile as well as host associated software agents. This paper proposes and demonstrates on-demand and just-in-time agent composition approach which is combined with run-time support for MASs. Run-time support is based on mission cost-efficiency and shared objectives which enable termination, generation, injection and replacement of software agents as the mission evolves at run-time. We present the formal underpinning of our approach and describe the prototype tool – called eHermes, which has been implemented using available agent platforms. Analysis and results of evaluating eHermes are presented and discussed.     

基于多Agent的中文智能检索模型

Internet已经成为全球信息系统，如何智能地在这个系统中对信息进行检索一直是热点问题。分布式人工智能的发展和Agent在各个领域的广泛应用，为这个问题的解决提供了技犬上的支持。提出了一种基于多Agent的搜索模型，此模型可以根据不同需求进行信息的智能检索。     

Coordination of intelligent agents in real-time search

Search is a fundamental problem-solving method in artificial intelligence. Traditional off-line search algorithms attempt to find an optimal solution whereas real-time search algorithms try to find a suboptimal solution more quickly than traditional algorithms to meet real-time constraints. In this work, a new multi-agent real-time search algorithm is developed and its effectiveness is illustrated on a sample domain, namely maze problems. Searching agents can see their environment with a specified visual depth and hence can partially observe their environment. An agent makes use of its partial observation to select a next move, instead of using only one-move-ahead information. Furthermore agents cooperate through a marking mechanism to be able to search different parts of the search space. When an agent selects its next move, it marks its direction of move before executing the move. When another agent comes to this position, it sees this mark and, if possible, moves in a different direction than the previously selected direction. In this way, marking helps agents coordinate their moves with other agents. Although coordination brings an overhead, from experiments we observe that this mechanism is effective in both search time and solution length in maze problems.     

多Agent系统的技术研究

多Agent系统是由多个智能Agent组成的有机系统,这使得它具有比单个Agent更强大的处理能力。它表出自组织性、鲁棒性、分布性以及很强的复杂行为。文中论述了Agent和多Agent系统的有关理论、方法和技术。主要包括智能Agent的特性、结构和推理;介绍多Agent系统的体系结构分类和常见的几种通信机制;以及面向Agent的程序设计的现状和发展。     

Multi-agent Mediator architecture for distributed manufacturing

A generic Mediator architecture for distributed task planning and coordination has been developed using multi-agent paradigms. In this approach, agents function autonomously as independent computing processes, and dynamic virtual clusters coordinate the agent's activities and decision making. This coordination involves dynamically created coordination agents and resource agents concurrently. The Mediator architecture contains three levels of these coordination agents: the template mediator, the data-agent manager, and the active mediator. The template mediator is the top-level global coordinator. This agent contains both the templates and the cloning mechanism to create the successively lower-level agents. Task plans are decomposed successively into subtasks, which are allocated to dynamically created agent clusters coordinated through data-agent managers and active mediators. Coordination of agent activity takes place both among the clusters and within each cluster. The system dynamically adapts to evolving manufacturing tasks, with virtual agent clusters being created as needed, and destroyed when their tasks are completed. The mediator architecture and related mechanisms are demonstrated using an intelligent manufacturing scheduling application. Both the machines and the parts involved in this production system are considered as intelligent agents. These agents use a common language protocol based on the Knowledge Query Manipulation Language (KQML). The generic Mediator approach can be used for other distributed organizational systems beyond the intelligent manufacturing application it was originally developed for.     

一种基于社会承诺的Agent组织模型OMSC

多Agent领域所面临的一个重大的挑战是解决开放异质的多Agent系统中自治Agent间的协调问题。多Agent为了协调它们之间的活动,需要进行交互。社会承诺作为一种通信和交互机制,为自治的多Agent提供了一种协调的途径。然而,仅靠交互难以实现多Agent间的协调。Agent组织作为一种协调模型可以有效地控制多Agent间的交互与合作。论文将社会承诺和Agent组织两种协调机制相结合,提出一种基于社会承诺的Agent组织模型OMSC,分析了Agent如何用社会承诺进行推理以及基于社会承诺的多Agent系统并给出了一个实例,为多Agent间的协调提供了一种新的方法。