This article summarizes 16 agent strategies that were designed for the 2002 Trading Agent Competition. Agent architects use numerous general-purpose AI techniques, including machine learning, planning, partially observable Markov decision processes, Monte Carlo simulations, and multiagent systems. Ultimately, the most successful agents were primarily heuristic based and domain specific.

The Trading Agent Competition (TAC) has now become an annual fixture since its inception in 2000. The competition was conceived with the objective of studying automated trading strategies by focusing the research community on the development of competing solutions to a common trading scenario. The success of past TAC events has motivated broadening the scope of the competition beyond the context of the travel agent scenario used thus far. For the fourth edition of this competition, TAC-03, to be held in August 2003, the authors have created a novel supply-chain trading game with the aim of investigating automated agents in the context of dynamic supply-chain management.

Life meetings have grown from small www.comp.hkbu.edu.hk/IAT03/

However, even if you become aware of the value of a chance event, for example, with a new behavior of a customer in the market you are selling in, it is still hard to persuade your colleagues to make actions in response to the rare event. "Interesting keywords arose, such as "You had a symposium on the creation The Symposium on Etiquette for Human-Computer "So was it a conference on knowledge Work began its meeting--with discovery inviting philosophers?" The first invited talk In this symposium, we had 17 papers, Jeanne Comeau, an author, speaker, gave us deep insight into customer 2 invited lectures, and 14 other and teacher on etiquette and the director networks in the market, and the last speakers. Six countries (Japan, United of the Etiquette School of panel extended to management, persuasion, States, United Kingdom, Germany, Boston. Comeau taught us a great communication, and trust, Portugal, and the Czech Republic) deal about etiquette's history and and so on.

Customers issue requests for quotes and select from quotes submitted by the PC assemblers, based on delivery dates and prices. In today's global economy, of components: (1) central processing units effective supply-chain management is vital (CPUs), (2) motherboards, (3) memory units, to the competitiveness of manufacturing enterprises and (4) disk drives. It features a variety of components because it directly impacts their ability of each type (for example, different to meet changing market demands in a timely CPUs, different motherboards). With annual worldwide comes in the form of requests for quotes supply-chain transactions in the trillions for different types of PCs, each requiring a different of dollars, the potential impact of performance combination of components. Although today's The PC assembly agents compete over a relatively supply chains are essentially static, relying long period of time during which customer on long-term relationships among key demand and availability of supplies trading partners, more flexible and dynamic varies according to predefined stochastic distributions practices offer the prospect of better matches (figure 1).

In TAC-00, agent designs were primarily centered around designing algorithms a tripod are sometimes bundled with the camera to solve an NPcomplete optimization and sometimes auctioned separately. However, by the second year, it for the next generation of trading agents, became common knowledge that this problem autonomous bidding in simultaneous auctions was tractable for the TAC travel game parameters. During the second year, agent designs focused Simultaneous auctions, which characterize on estimating clearing prices, and some internet sites such as eBay.com, Agent design in and substitutable goods are on offer. Complementary TAC-02, however, cannot be described so succinctly.

There is an increasing need for automated support for humans monitoring the activity of distributed teams of cooperating agents, both human and machine. We characterize the domain-independent challenges posed by this problem, and describe how properties of domains influence the challenges and their solutions. We will concentrate on dynamic, data-rich domains where humans are ultimately responsible for team behavior. Thus, the automated aid should interactively support effective and timely decision making by the human. We present a domain-independent categorization of the types of alerts a plan-based monitoring system might issue to a user, where each type generally requires different monitoring techniques. We describe a monitoring framework for integrating many domain-specific and task-specific monitoring techniques and then using the concept of value of an alert to avoid operator overload. We use this framework to describe an execution monitoring approach we have used to implement Execution Assistants (EAs) in two different dynamic, data-rich, real-world domains to assist a human in monitoring team behavior. One domain (Army small unit operations) has hundreds of mobile, geographically distributed agents, a combination of humans, robots, and vehicles. The other domain (teams of unmanned ground and air vehicles) has a handful of cooperating robots. Both domains involve unpredictable adversaries in the vicinity. Our approach customizes monitoring behavior for each specific task, plan, and situation, as well as for user preferences. Our EAs alert the human controller when reported events threaten plan execution or physically threaten team members. Alerts were generated in a timely manner without inundating the user with too many alerts (less than 10 percent of alerts are unwanted, as judged by domain experts).

We describe a new algorithm for computing a Nash equilibrium in graphical games, a compact representation for multi-agent systems that we introduced in previous work. The algorithm is the first to compute equilibria both efficiently and exactly for a nontrivial class of graphical games. 1 Introduction Seeking to replicate the representational and computational benefits that graphical models have provided to probabilistic inference, several recent works have introduced graph-theoretic frameworks for the study of multi-agent systems (La Mura 2000; Koller and Milch 2001; Kearns et al. 2001). In the simplest of these formalisms, each vertex represents a single agent, and the edges represent pairwise interaction between agents. As with many familiar network models, the macroscopic behavior of a large system is thus implicitly described by its local interactions, and the computational challenge is to extract the global states of interest. Classical game theory is typically used to model multi-agent interactions, and the global states of interest are thus the so-called Nash equilibria, in which no agent has a unilateral incentive to deviate.

We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication between the agents is not imposed, but derived directly from the system dynamics and function approximation architecture. We view the entire multiagent system as a single, large Markov decision process (MDP), which we assume can be represented in a factored way using a dynamic Bayesian network (DBN). The action space of the resulting MDP is the joint action space of the entire set of agents. Our approach is based on the use of factored linear value functions as an approximation to the joint value function.

We propose a new classification for multi-agent learning algorithms, with each league of players characterized by both their possible strategies and possible beliefs. Using this classification, we review the optimality of existing algorithms, including the case of interleague play. We propose an incremental improvement to the existing algorithms that seems to achieve average payoffs that are at least the Nash equilibrium payoffs in the longrun against fair opponents.