Decentralized MDPs with sparse interactions

Creating coordinated multiagent policies in environments with uncertainty is a challenging problem, which can be greatly simplified if the coordination needs are known to be limited to specific parts of the state space. In this work, we explore how such local interactions can simplify coordination in multiagent systems. We focus on problems in which the interaction between the agents is sparse and contribute a new decision-theoretic model for decentralized sparse-interaction multiagent systems, Dec-SIMDPs, that explicitly distinguishes the situations in which the agents in the team must coordinate from those in which they can act independently. We relate our new model to other existing models such as MMDPs and Dec-MDPs. We then propose a solution method that takes advantage of the particular structure of Dec-SIMDPs and provide theoretical error bounds on the quality of the obtained solution. Finally, we show a reinforcement learning algorithm in which independent agents learn both individual policies and when and how to coordinate. We illustrate the application of the algorithms throughout the paper in several multiagent navigation scenarios.     

Design of coordination strategies in multiagent systems via genetic fuzzy systems

This paper suggests an evolutionary approach to design coordination strategies for multiagent systems. Emphasis is given to auction protocols since they are of utmost importance in many real world applications such as power markets. Power markets are one of the most relevant instances of multiagent systems and finding a profitable bidding strategy is a key issue to preserve system functioning and improve social welfare. Bidding strategies are modeled as fuzzy rule-based systems due to their modeling power, transparency, and ability to naturally handle imprecision in input data, an essential ingredient to a multiagent system act efficiently in practice. Specific genetic operators are suggested in this paper. Evolution of bidding strategies uncovers unknown and unexpected agent behaviors and allows a richer analysis of auction mechanisms and their role as a coordination protocol. Simulation experiments with a typical power market using actual thermal plants data show that the evolutionary, genetic-based design approach evolves strategies that enhance agents profitability when compared with the marginal cost-based strategies commonly adopted     

Environment as a first class abstraction in multiagent systems

The current practice in multiagent systems typically associates the environment with resources that are external to agents and their communication infrastructure. Advanced uses of the environment include infrastructures for indirect coordination, such as digital pheromones, or support for governed interaction in electronic institutions. Yet, in general, the notion of environment is not well defined. Functionalities of the environment are often dealt with implicitly or in an ad hoc manner. This is not only poor engineering practice, it also hinders engineers to exploit the full potential of the environment in multiagent systems. In this paper, we put forward the environment as an explicit part of multiagent systems.We give a definition stating that the environment in a multiagent system is a first-class abstraction with dual roles: (1) the environment provides the surrounding conditions for agents to exist, which implies that the environment is an essential part of every multiagent system, and (2) the environment provides an exploitable design abstraction for building multiagent system applications. We discuss the responsibilities of such an environment in multiagent systems and we present a reference model for the environment that can serve as a basis for environment engineering. To illustrate the power of the environment as a design abstraction, we show how the environment is successfully exploited in a real world application. Considering the environment as a first-class abstraction in multiagent systems opens up new horizons for research and development in multiagent systems.     

Coordinated learning by exploiting sparse interaction in multiagent systems

Multiagent learning provides a promising paradigm to study how autonomous agents learn to achieve coordinated behavior in multiagent systems. In multiagent learning, the concurrency of multiple distributed learning processes makes the environment nonstationary for each individual learner. Developing an efficient learning approach to coordinate agents’ behavior in this dynamic environment is a difficult problem especially when agents do not know the domain structure and at the same time have only local observability of the environment. In this paper, a coordinated learning approach is proposed to enable agents to learn where and how to coordinate their behavior in loosely coupled multiagent systems where the sparse interactions of agents constrain coordination to some specific parts of the environment. In the proposed approach, an agent first collects statistical information to detect those states where coordination is most necessary by considering not only the potential contributions from all the domain states but also the direct causes of the miscoordination in a conflicting state. The agent then learns to coordinate its behavior with others through its local observability of the environment according to different scenarios of state transitions. To handle the uncertainties caused by agents’ local observability, an optimistic estimation mechanism is introduced to guide the learning process of the agents. Empirical studies show that the proposed approach can achieve a better performance by improving the average agent reward compared with an uncoordinated learning approach and by reducing the computational complexity significantly compared with a centralized learning approach. Copyright © 2012 John Wiley & Sons, Ltd.     

ACHIEVING FLEXIBLE AUTONOMY IN MULTIAGENT SYSTEMS USING CONSTRAINTS

Organizations influence many aspects of our lives. They exist for one reason: they can accomplish things that individuals cannot. While recent work in high-autonomy systems has shown that autonomy is a critical issue in artificial intelligence (AI) systems, these systems must also be able to cooperate with and rely on one another to deal with complex problems. The autonomy of such systems must be flexible, in order that agents may solve problems on their own as well as in groups. We have developed a model of distributed problem solving in which coordination of problem-solving agents is viewed as a multiagent constraint-satisfaction planning problem. This paper describes the experimental testbed that we are currently developing to facilitate the investigation of various constraint-based strategies for addressing the coordination issues inherent in cooperative distributed problem-solving domains.     

Adaptive architectures for resilient control of networked multiagent systems in the presence of misbehaving agents

Control algorithms of networked multiagent systems are generally computed distributively without having a centralised entity monitoring the activity of agents; and therefore, unforeseen adverse conditions such as uncertainties or attacks to the communication network and/or failure of agent-wise components can easily result in system instability and prohibit the accomplishment of system-level objectives. In this paper, we study resilient coordination of networked multiagent systems in the presence of misbehaving agents, i.e. agents that are subject to exogenous disturbances that represent a class of adverse conditions. In particular, a distributed adaptive control architecture is presented for directed and time-varying graph topologies to retrieve a desired networked multiagent system behaviour. Apart from the existing relevant literature that make specific assumptions on the graph topology and/or the fraction of misbehaving agents, we show that the considered class of adverse conditions can be mitigated by the proposed adaptive control approach that utilises a local state emulator – even if all agents are misbehaving. Illustrative numerical examples are provided to demonstrate the theoretical findings.     

TRAMMAS: A tracing model for multiagent systems

Agent's flexibility and autonomy, as well as their capacity to coordinate and cooperate, are some of the features which make multiagent systems useful to work in dynamic and distributed environments. These key features are directly related to the way in which agents communicate and perceive each other, as well as their environment and surrounding conditions. Traditionally, this has been accomplished by means of message exchange or by using blackboard systems. These traditional methods have the advantages of being easy to implement and well supported by multiagent platforms; however, their main disadvantage is that the amount of social knowledge in the system directly depends on every agent actively informing of what it is doing, thinking, perceiving, etc. There are domains, for example those where social knowledge depends on highly distributed pieces of data provided by many different agents, in which such traditional methods can produce a great deal of overhead, hence reducing the scalability, efficiency and flexibility of the multiagent system. This work proposes the use of event tracing in multiagent systems, as an indirect interaction and coordination mechanism to improve the amount and quality of the information that agents can perceive from both their physical and social environment, in order to fulfill their goals more efficiently. In order to do so, this work presents an abstract model of a tracing system and an architectural design of such model, which can be incorporated to a typical multiagent platform.     

面向自动文摘的多Agent系统中的协调算法研究

为了解决自动文摘系统所面临的领域通用性和文摘质量的矛盾,提出了建造面向自动文摘的多Aent系统（MAS／ABS)的方案。建造这样的系统,有两个关键问题：建立什么样的系统模型和选择什么样的协调算法。给出了在Internet环境下面向自动文摘的多Agent系统模型,提出了3种协调算法。在仿真的基础上分析了系统性能,对3种协调算法进行了比较研究,并得到了在一定负载下面向各个领域合适的文摘Agent数目。     

Opportunities for multiagent systems and multiagent reinforcement learning in traffic control

The increasing demand for mobility in our society poses various challenges to traffic engineering, computer science in general, and artificial intelligence and multiagent systems in particular. As it is often the case, it is not possible to provide additional capacity, so that a more efficient use of the available transportation infrastructure is necessary. This relates closely to multiagent systems as many problems in traffic management and control are inherently distributed. Also, many actors in a transportation system fit very well the concept of autonomous agents: the driver, the pedestrian, the traffic expert; in some cases, also the intersection and the traffic signal controller can be regarded as an autonomous agent. However, the “agentification” of a transportation system is associated with some challenging issues: the number of agents is high, typically agents are highly adaptive, they react to changes in the environment at individual level but cause an unpredictable collective pattern, and act in a highly coupled environment. Therefore, this domain poses many challenges for standard techniques from multiagent systems such as coordination and learning. This paper has two main objectives: (i) to present problems, methods, approaches and practices in traffic engineering (especially regarding traffic signal control); and (ii) to highlight open problems and challenges so that future research in multiagent systems can address them.