Multiagent learning is a key problem in AI. In the presence of multiple Nashequilibria, even agents with non-conflicting interests may not be able to learn an optimal coordination policy. The problem is exaccerbated ifthe agents do not know the game and independently receive noisy payoffs. So, multiagent reinforfcement learning involves two interrelated problems:identifying the game and learning to play.

We present a new method for learning good strategies in zero-sum Markov games in which each side is composed of multiple agents collaborating againstan opposing team of agents. Our method requires full observability and communication during learning, but the learned policies canbe executed in a distributed manner. The value function is represented asa factored linear architecture and its structure determines the necessary computational resources and communication bandwidth. This approach permits a tradeoff between simple representations with little or no communication between agents and complex, computationally intensive representationswith extensive coordination between agents. Thus, we provide a principled means of using approximation to combat the exponential blowup in the joint action space of the participants. The approach isdemonstrated with an example that shows the efficiency gains over naive enumeration.

Program (July 28) is currently accepting nominations accessible to the general public or Tenth AAAI/SIGART Doctoral Consortium for AAAI Fellow. The AAAI Fellows to a broad AI audience (not just a subarea), (July 25-26) program is designed to written within the last two AAAI Intelligent Systems Demonstrations recognize people who have made significant, years.

Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative teachers or other more experienced agents. We propose and study a formal model of implicit imitation that can accelerate reinforcement learning dramatically in certain cases. Roughly, by observing a mentor, a reinforcement-learning agent can extract information about its own capabilities in, and the relative value of, unvisited parts of the state space. We study two specific instantiations of this model, one in which the learning agent and the mentor have identical abilities, and one designed to deal with agents and mentors with different action sets. We illustrate the benefits of implicit imitation by integrating it with prioritized sweeping, and demonstrating improved performance and convergence through observation of single and multiple mentors. Though we make some stringent assumptions regarding observability and possible interactions, we briefly comment on extensions of the model that relax these restricitions.

Supply chain formation is the process of determining the structure and terms of exchange relationships to enable a multilevel, multiagent production activity. We present a simple model of supply chains, highlighting two characteristic features: hierarchical subtask decomposition, and resource contention. To decentralize the formation process, we introduce a market price system over the resources produced along the chain. In a competitive equilibrium for this system, agents choose locally optimal allocations with respect to prices, and outcomes are optimal overall. To determine prices, we define a market protocol based on distributed, progressive auctions, and myopic, non-strategic agent bidding policies. In the presence of resource contention, this protocol produces better solutions than the greedy protocols common in the artificial intelligence and multiagent systems literature. The protocol often converges to high-value supply chains, and when competitive equilibria exist, typically to approximate competitive equilibria. However, complementarities in agent production technologies can cause the protocol to wastefully allocate inputs to agents that do not produce their outputs. A subsequent decommitment phase recovers a significant fraction of the lost surplus.

Hierarchical task decomposition is a method used in many agent systems to organize agent knowledge. This work shows how the combination of a hierarchy and persistent assertions of knowledge can lead to difficulty in maintaining logical consistency in asserted knowledge. We explore the problematic consequences of persistent assumptions in the reasoning process and introduce novel potential solutions. Having implemented one of the possible solutions, Dynamic Hierarchical Justification, its effectiveness is demonstrated with an empirical analysis.

(ICKEDS 2004). GECAD--Knowledge Engineering and ICINCO Secretariat Decision Support Research Group Escola Superior de Tecnologia de Setubal Rua Dr. Antonio Bernardino Almeida / Campus do IPS

The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, presented the 2003 Spring Symposium Series, Monday through Wednesday, 24-26 March 2003, at Stanford University. The titles of the eight symposia were Agent-Mediated Knowledge Management, Computational Synthesis: From Basic Building Blocks to High- Level Functions, Foundations and Applications of Spatiotemporal Reasoning (FASTR), Human Interaction with Autonomous Systems in Complex Environments, Intelligent Multimedia Knowledge Management, Logical Formalization of Commonsense Reasoning, Natural Language Generation in Spoken and Written Dialogue, and New Directions in Question-Answering Motivation.

We consider the two-fold problem of representing collective beliefs and aggregating these beliefs. We propose a novel representation for collective beliefs that uses modular, transitive relations over possible worlds. They allow us to represent conflicting opinions and they have a clear semantics, thus improving upon the quasi-transitive relations often used in social choice. We then describe a way to construct the belief state of an agent informed by a set of sources of varying degrees of reliability. This construction circumvents Arrow's Impossibility Theorem in a satisfactory manner by accounting for the explicitly encoded conflicts. We give a simple set-theory-based operator for combining the information of multiple agents. We show that this operator satisfies the desirable invariants of idempotence, commutativity, and associativity, and, thus, is well-behaved when iterated, and we describe a computationally effective way of computing the resulting belief state. Finally, we extend our framework to incorporate voting.

I'm delighted to bring our readers the news of an exciting resource for AAAI members. AAAI has now completed a major initiative, begun five years ago, to develop a digital library of AAAI publications. The collection now comprises approximately 13,000 papers, including the full set of papers from the AAAI proceedings, papers from other major conferences, AAAI workshop and symposium technical reports, selected AAAI Press books, and the full contents of AI Magazine. This already-extensive collection is a growing resource, with new publications and access methods to be added over time. I encourage readers to visit it at the members' library section of the AAAI web site, www.aaai.org.