Many researchers have demonstrated that the organizational design employed by an agent system can have a significant, quantitative effect on its performance characteristics. A range of organizational strategies have emerged from this line of research, each with different strengths and weaknesses. In this article we present a survey of the major organizational paradigms used in multi-agent systems. These include hierarchies, holarchies, coalitions, teams, congregations, societies, federations, markets, and matrix organizations. We will provide a description of each, discuss their advantages and disadvantages, and provide examples of how they may be instantiated and maintained. This summary will facilitate the comparative evaluation of organizational styles, allowing designers to first recognize the spectrum of possibilities, and then guiding the selection of an appropriate organizational design for a particular domain and environment.

No abstract

This paper analyzes coalitions among self-interested agents that need to solve combinatorial optimization problems to operate e ciently in the world. By colluding coordinating their actions by solving a joint optimization problem the agents can sometimes save costs compared to operating individually. A model of bounded r ationality is adopted where computation resources are costly. It is not worthwhile solving the problems optimally: solution quality is decision-theoretically traded o against computation cost. A normative, application-and protocol-independent theory of coalitions among boundedrational agents is devised. The optimal coalition structure and its stability are signi cantly a ected by the agents' algorithms' performance pro les and the cost of computation. This relationship is rst analyzed theoretically. Then a domain classi cation including rational and bounded-rational agents is introduced. Experimental results are presented in vehicle routing with real data from ve dispatch centers. This problem is NP-complete and the instances are so large that|with current technology|any agent's rationality is bounded by computational complexity.

No abstract

Formal treatment of collaborative multi-agent systems has been lagging behind the rapid progress in sequential decision making by individual agents. Recent work in the area of decentralized Markov Decision Processes (MDPs) has contributed to closing this gap, but the computational complexity of these models remains a serious obstacle. To overcome this complexity barrier, we identify a specific class of decentralized MDPs in which the agents' transitions are independent. The class consists of independent collaborating agents that are tied together through a structured global reward function that depends on all of their histories of states and actions. We present a novel algorithm for solving this class of problems and examine its properties, both as an optimal algorithm and as an anytime algorithm. To our best knowledge, this is the first algorithm to optimally solve a non-trivial subclass of decentralized MDPs. It lays the foundation for further work in this area on both exact and approximate algorithms.

There has been substantial progress with formal models for sequential decision making by individual agents using the Markov decision process (MDP). However, similar treatment of multi-agent systems is lacking. A recent complexity result, showing that solving decentralized MDPs is NEXPhard, provides a partial explanation. To overcome this complexity barrier, we identify a general class of transitionindependent decentralized MDPs that is widely applicable. The class consists of independent collaborating agents that are tied up by a global reward function that depends on both of their histories. We present a novel algorithm for solving this class of problems and examine its properties. The result is the first effective technique to solve optimally a class of decentralized MDPs. This lays the foundation for further work in this area on both exact and approximate solutions.

The Hearsay-II system, developed during the DARPA-sponsored five-year speechunderstanding research program, represents both a specific solution to the speechunderstanding problem and a general framework for coordinating independent processes to achieve cooperative problem-solving behavior. As a computational problem, speech understanding reflects a large number of intrinsically interesting issues. Spoken sounds are achieved by a long chain of successive transformations, from intentions, through semantm and syntactic structurmg, to the eventually resulting audible acoustic waves. As a consequence, interpreting speech means effectively inverting these transformations to recover the speaker's intention from the sound. At each step in the interpretive process, ambiguity and uncertainty arise. The Hearsay-II problem-solving framework reconstructs an intention from hypothetmal interpretations formulated at various levels of abstraction. In additmn, it allocates hmlted processing resources fwst to the most promising incremental actions. The final configuration of the Hearsay-II system comprises problem-solving components to generate and evaluate speech hypotheses, and a focus-of-control mechanism to identify potentml actions of greatest value. Many of these specific procedures reveal novel approaches to speech problems. Most important, the system successfully integrates and coordinates all of these independent actlwhes to resolve uncertainty and control combmatorms. Several adaptations of the Hearsay-II framework have already been undertaken in other problem domains, and it is anticipated that this trend will contmue; many future systems necessarily will integrate diverse sources of knowledge to solve complex problems cooperatively. Discussed m this paper are the characteristics of the speech problem in particular, the specml kinds of problem-solving uncertainty in that domain, the structure of the Hearsay-II system developed to cope with that uncertamty, and the relationship between Hearsay-Irs structure and those of other speech-understanding systems. The paper is intended for the general computer science audience and presupposes no speech or artificial intelligence background.

For distributed sensor network applications, a practical approach to generating complete interpretations from distributed data must coordinate how separate, concurrently running systems form, exchange, and fuse their individual hypotheses to form consistent interpretations. Partial global planning provides a framework for coordinating multiple AI systems that are cooperating in a distributed sensor network. By combining a variety of coordination techniques into a single, unifying framework, partial global planning enables separate AI systems to reason about their roles and responsibilities as part of group problem solving, and to modify their planned processing and communication actions to act as a more coherent team. Partial global planning is uniquely suited for coordinating systems that are working in continuous, dynamic, and unpredictable domains because it interleaves coordination with action and allows systems to make effective decisions despite incomplete and possibly obsolete information about network activity. The authors have implemented and extensively evaluated partial global planning in a simulated vehicle monitoring application, and have identified promising extensions to their framework Manuscript