From the Publisher:
An agent is an entity with domain knowledge, goals and actions. Multi-agent systems are a set of agents which
interact in a common environment. Multi-agent systems deal with the construction of complex systems involving multiple agents and their coordination. A multi-agent system (MAS) is a distributed computing system with
autonomous interacting intelligent agents that coordinate their actions so as to achieve its goal(s) jointly or competitively.

Introduction to Multiagent Systems

Model-based Bayesian Reinforcement Learning (BRL) provides a principled solution to dealing with the exploration-exploitation trade-off, but such methods typically assume a fully observable environments. The few Bayesian RL methods that are applicable in partially observable domains, such as the Bayes-Adaptive POMDP (BA-POMDP), scale poorly. To address this issue, we introduce the Factored BA-POMDP model (FBA-POMDP), a framework that is able to learn a compact model of the dynamics by exploiting the underlying structure of a POMDP. The FBA-POMDP framework casts the problem as a planning task, for which we adapt the Monte-Carlo Tree Search planning algorithm and develop a belief tracking method to approximate the joint posterior over the state and model variables. Our empirical results show that this method outperforms a number of BRL baselines and is able to learn efficiently when the factorization is known, as well as learn both the factorization and the model parameters simultaneously.

/pdf/bayesian-reinforcement-learning-in-factored-pomdps-xpra8a8w97.pdf

Bayesian Reinforcement Learning in Factored POMDPs

Methods for task allocation via agent coalition formation

In Retsina, the authors have developed a distributed collection of software agents that cooperate asynchronously to perform goal-directed information retrieval and integration for supporting a variety of decision-making tasks. Examples for everyday organizational decision making and financial portfolio management demonstrate its effectiveness.

/pdf/distributed-intelligent-agents-414mvmm343.pdf

Distributed intelligent agents

Service matchmaking among heterogeneous software agents in the Internet is usually done dynamically and must be efficient. There is an obvious trade-off between the quality and efficiency of matchmaking on the Internet. We define a language called Larks for agent advertisements and requests, and present a flexible and efficient matchmaking process that uses Larks. The Larks matchmaking process performs both syntactic and semantic matching, and in addition allows the specification of concepts (local ontologies) via ITL, a concept language. The matching process uses five different filters: context matching, profile comparison, similarity matching, signature matching and constraint matching. Different degrees of partial matching can result from utilizing different combinations of these filters. We briefly report on our implementation of Larks and the matchmaking process in Java. Fielded applications of matchmaking using Larks in several application domains for systems of information agents are ongoing efforts.

/pdf/larks-dynamic-matchmaking-among-heterogeneous-software-1099t2aif7.pdf

Larks: Dynamic Matchmaking Among Heterogeneous Software Agents in Cyberspace

Factors such as the massive increase in information available via electronic networks and the advent of virtual distributed workgroups for commerce are placing severe burdens on traditional methods of information sharing and retrieval. Matchmaking proposes an intelligent facilitation agent that accepts machine-readable requests and advertisements from information consumers and providers, and determines potential information sharing paths. We argue that matchmaking permits large numbers of dynamic consumers and providers, operating on rapidly-changing data, to share information more effectively than via current methods. This paper introduces matchmaking, as enabled by knowledge sharing standards like KQML, and describes the SHADE and COINS matchmaker implementations. The utility and initial results of matchmaking are illustrated via example scenarios in engineering and consumer information retrieval.

/pdf/matchmaking-for-information-agents-33dqd2ag1o.pdf

Matchmaking for information agents

As agents see more use as entry points to incxeasingly complex distributed information networks, agent communication technologies such as the Knowledge Query and Manipulation Language and the SHADE Matchmaker will play an important role. We describe our experiences with these technologies as applied to two applications: collaborative engineering and satellite image retrieval. Based on these experiences, we outline the major observed benefits of KQML and matchmaking. In addition, we discuss several problematic issues and potential solutions, including representational challenges in advertising complex databases, the need for persistent requests in information brokering, the dilemm~ between explicit vs. implicit brokering, problems in error recovery and response timing, consistency among information providers, and efficiency.

/pdf/on-using-kqml-for-matchmaking-15gv9er669.pdf

On Using KQML for Matchmaking

Trends such as the massive increase in information available via electronic networks, the use of on-line product data by distributed concurrent engineering teams, and dynamic supply chain integration for electronic commerce are placing severe burdens on traditional methods of information sharing and retrieval. Sources of information are far too numerous and dynamic to be found via traditional information retrieval methods, and potential consumers are seeing increased need for automatic notification services. Matchmaking is an approach based on emerging information integration technologies whereby potential producers and consumers of information send messages describing their information capabilities and needs. These descriptions, represented in rich, machine-interpretable description languages, are unified by the matchmaker to identify potential matches. Based on the matches, a variety of information brokering services are performed. We introduce matchmaking, and argue that it permits large numbers of dynamic consumers and providers, operating on rapidly-changing data, to share information more effectively than via traditional methods. Two matchmakers are described, the SHADE matchmaker, which operates over logic-based and structured text languages, and the COINS matchmaker, which operates over free text. These matchmakers have been used for a variety of applications, most significantly, in the domains of engineering and electronic commerce. We describe our experiences with the SHADE and COINS matchmaker, and we outline the major observed benefits and problems of matchmaking.

Integrating information via matchmaking

The massive increase in information available via electronic networks is placing severe burdens on traditional methods of information sharing and retrieval. Matchmaking proposes an intelligent facilitation agent that accepts machine-readable requests and advertisements from information consumers and providers, and determines potential information sharing paths. Matchmaking permits large nmnbers of dynamic consumers and providers, operating on rapidly-changing data, to locate and share information effectively. This paper introduces matchmaking, as enabled by knowledge sharing standards like KQML, and gives a brief description of the the SHADE and COINS matchmakers. In addition, several applications are described to illustrate the utility of matchmaking for information retrieval.

/pdf/supporting-information-retrieval-via-matchmaking-3uqaka7cor.pdf

Supporting Information Retrieval via Matchmaking

Integrating multiple engineering perspectives is critical to designing ever more complex products, but this introduces great potential for miscommunication leading to design conflicts. The SHADE (SHAred Dependency Engineering) project is defining agent infrastructure technology that supports dynamic, knowledge-based communication among heterogeneous engineering tools, collaboration systems, and conflict management systems. Building on technologies for defining a shared formal vocabulary and protocols for exchanging information, SHADE is developing facilitators that assist in locating and disseminating information. The result is a flexible infrastructure that helps existing engineering tools work together more effectively, and that supports a variety of new conflict management approaches. This article outlines the facilitation and application agents created by SHADE, and provides an in-depth example of their application to an engineering task.

Daniel Kuokka

Papers

Matchmaking for information agents

On Using KQML for Matchmaking

Integrating information via matchmaking

Supporting Information Retrieval via Matchmaking

Communication infrastructure for concurrent engineering