DART: A DISTRIBUTED ANALYSIS OF REPUTATION AND TRUST FRAMEWORK

Artificial societies—distributed systems of autonomous agents—are becoming increasingly important in open distributed environments, especially in e‐commerce. Agents require trust and reputation concepts to identify communities of agents with which to interact reliably. We have noted in real environments that adversaries tend to focus on exploitation of the trust and reputation model. These vulnerabilities reinforce the need for new evaluation criteria for trust and reputation models called exploitation resistance which reflects the ability of a trust model to be unaffected by agents who try to manipulate the trust model. To examine whether a given trust and reputation model is exploitation‐resistant, the researchers require a flexible, easy‐to‐use, and general framework. This framework should provide the facility to specify heterogeneous agents with different trust models and behaviors. This paper introduces a Distributed Analysis of Reputation and Trust (DART) framework. The environment of DART is decentralized and game‐theoretic. Not only is the proposed environment model compatible with the characteristics of open distributed systems, but it also allows agents to have different types of interactions in this environment model. Besides direct, witness, and introduction interactions, agents in our environment model can have a type of interaction called a reporting interaction, which represents a decentralized reporting mechanism in distributed environments. The proposed environment model provides various metrics at both micro and macro levels for analyzing the implemented trust and reputation models. Using DART, researchers have empirically demonstrated the vulnerability of well‐known trust models against both individual and group attacks.     

Learning Sequences of Compatible Actions Among Agents

Action coordination in multiagent systemsis a difficult task especially in dynamicenvironments. If the environment possessescooperation, least communication,incompatibility and local informationconstraints, the task becomes even moredifficult. Learning compatible action sequencesto achieve a designated goal under theseconstraints is studied in this work. Two newmultiagent learning algorithms called QACE andNoCommQACE are developed. To improve theperformance of the QACE and NoCommQACEalgorithms four heuristics, stateiteration, means-ends analysis, decreasing reward and do-nothing, aredeveloped. The proposed algorithms are testedon the blocks world domain and the performanceresults are reported.     

Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments

Coordination is an essential technique in cooperative, distributed multiagent systems. However, sophisticated coordination strategies are not always cost-effective in all problem-solving situations. This paper presents a learning method to identify what information will improve coordination in specific problem-solving situations. Learning is accomplished by recording and analyzing traces of inferences after problem solving. The analysis identifies situations where inappropriate coordination strategies caused redundant activities, or the lack of timely execution of important activities, thus degrading system performance. To remedy this problem, situation-specific control rules are created which acquire additional nonlocal information about activities in the agent networks and then select another plan or another scheduling strategy. Examples from a real distributed problem-solving application involving diagnosis of a local area network are described.     

Level-of-detail for cognitive real-time characters

We present a solution for the real-time simulation of artificial environments containing cognitive and hierarchically organized agents at constant rendering framerates. We introduce a level-of-detail concept to behavioral modeling, where agents populating the world can be both reactive and proactive. The disposable time per rendered frame for behavioral simulation is variable and determines the complexity of the presented behavior. A special scheduling algorithm distributes this time to the agents depending on their level-of-detail such that visible and nearby agents get more time than invisible or distant agents. This allows for smooth transitions between reactive and proactive behavior. The time available per agent influences the proactive behavior, which becomes more sophisticated because it can spend time anticipating future situations. Additionally, we exploit the use of hierarchies within groups of agents that allow for different levels of control. We show that our approach is well-suited for simulating environments with up to several hundred agents with reasonable response times and the behavior adapts to the current viewpoint.     

基于递阶强化学习的多智能体AGV 调度系统

递阶强化学习是解决状态空间庞大的复杂系统智能体决策的有效方法。具有离散动态特性的AGV调度系统需要实时动态的调度方法,而具有MaxQ递阶强化学习能力的多智能体通过高效的强化学习方法和协作,可以实现AGV的实时调度。仿真实验证明了这种方法的有效性。     

基于面向对象着色Petri网的多Agent系统建模

提出了一种基于面向对象着色Petri网（OOCPN）的多Agent建模方法,与其它建模方法相比,OOCPN可以全面地刻画出Agent的个体行为特征和多Agent间复杂、并行的动态交互,讨论了利用OOCPN进行个体Agent和多Agent间交互协议的建模,并通过对网上智能购物系统的实例分析,展示了OOCPN对多Agent系统的建模能力。     

基于模糊竞争学习的非线性系统自适应模糊建模方法

提出了一种新的基于模糊竞争学习的自调整的模糊建模方法. 基于模糊竞争学习, 模糊系统能够进行自适应模糊推理. 在被调整模糊系统基础上, 提出了一种非线性系统在线估计参数的在线辨识算法. 为了证明提出算法的有效性, 最后给出了几个例子的仿真结果.