Software personal assistants continue to be a topic of significant research interest. This article outlines some of the important lessons learned from a successfully-deployed team of personal assistant agents (Electric Elves) in an office environment. In the Electric Elves project, a team of almost a dozen personal assistant agents were continually active for seven months. Each elf (agent) represented one person and assisted in daily activities in an actual office environment. This project led to several important observations about privacy, adjustable autonomy, and social norms in office environments. In addition to outlining some of the key lessons learned we outline our continued research to address some of the concerns raised.

These sorts of architectures were very much in vogue at the time, and the company wanted its own, proprietary technology. We started thinking about programming languages for the agents and the kinds of knowledge representation and reasoning that would be required. We spent a lot of time and money flying from London to the U.S. West Coast, talking to patent lawyers. It transpired that the architecture, its decision-making and action models, were completely inappropriate for the problem at hand. By the time we realized we should have been focusing on basic software engineering, quality assurance, and end-user requirements, the company had burned out much of the goodwill--and most of the funds--of our investors.

In fact, DARPA, which funded the project, ways. Elves) (Scerri, Pynadath, and Tambe 2002; Finally, we will present some lessons Pynadath and Tambe 2003) and required learned and recent research that was motivated detailed information about the calendars by our experiences in deploying the of people using the system. Thus, we decided to deploy a new application of the Electric The Travel Elves introduced two major Elves, called the Travel Elves. This application advantages over traditional approaches to appeared to be ideal for wider deployment travel planning. First, the Travel Elves provided since it could be hosted entirely outside an interactive approach to making an organization and communication travel plans in which all of the data could be performed over wireless devices, required to make informed choices is such as cellular telephones. For example, when The mission of the Travel Elves (Ambite deciding whether to park at the airport or et al. 2002, Knoblock 2004) was to facilitate take a taxi, the system compares the cost planning a trip and to ensure that the of parking and the cost of a taxi given other resulting travel plan would execute selections, such as the airport, the specific smoothly. Initial deployment of the Travel parking lot, and the starting location Elves at DARPA went smoothly.

We hope you are planning to join us for AAAI-08 and IAAI-08 in Chicago, Illinois, July 13-17, 2008. The AAAI-08 program will feature Eric Horvitz's cal papers will be highlighted as The program will include a research AAAI presidential address, as well as exceptional papers during the conference-wide track, industry track, invited speakers, five outstanding invited talks. Registration information invited speakers include Alexei A. Efros July 16, and another 23 short and other program details will (Carnegie Mellon University) whose papers will be presented as posters. Using Lots of Data to Infer Geometric, and awards will continue for its aiide08.php Please Photometric and Semantic Scene Properties second year with all the Hollywood send inquiries to aiide08@aaai.org

(ESAS 2008).

Extempo Systems, Inc. was founded in 1995 to commercialize intelligent characters. Our team built innovative software and novel applications for several markets. We had some early-adopting customers during the Internet boom, but the company was not quite able to survive the significant downturn in corporate IT spending when the bubble burst. In 2004, Extempo ceased operations and was formally liquidated. Although our commercial venture failed, we learned a lot, had fun, and are trying again with a new company. To others who aspire to commercialize their AI technology, I say: ";;Take a chance!";;

This paper presents a Multi-Agent approach to the problem of recommending training courses to engineering professionals. The recommendation system is built as a proof of concept and limited to the electrical and mechanical engineering disciplines. Through user modelling and data collection from a survey, collaborative filtering recommendation is implemented using intelligent agents. The agents work together in recommending meaningful training courses and updating the course information. The system uses a users profile and keywords from courses to rank courses. A ranking accuracy for courses of 90% is achieved while flexibility is achieved using an agent that retrieves information autonomously using data mining techniques from websites. This manner of recommendation is scalable and adaptable. Further improvements can be made using clustering and recording user feedback.

Crisis response poses many of the most difficult information technology in crisis management. It requires information and communication-intensive efforts, utilized for reducing uncertainty, calculating and comparing costs and benefits, and managing resources in a fashion beyond those regularly available to handle routine problems. In this paper, we explore the benefits of artificial intelligence technologies in crisis response. This paper discusses the role of artificial intelligence technologies; namely, robotics, ontology and semantic web, and multi-agent systems in crisis response.

Multi-agent planning in stochastic environments can be framed formally as a decentralized Markov decision problem. Many real-life distributed problems that arise in manufacturing, multi-robot coordination and information gathering scenarios can be formalized using this framework. However, finding the optimal solution in the general case is hard, limiting the applicability of recently developed algorithms. This paper provides a practical approach for solving decentralized control problems when communication among the decision makers is possible, but costly. We develop the notion of communication-based mechanism that allows us to decompose a decentralized MDP into multiple single-agent problems. In this framework, referred to as decentralized semi-Markov decision process with direct communication (Dec-SMDP-Com), agents operate separately between communications. We show that finding an optimal mechanism is equivalent to solving optimally a Dec-SMDP-Com. We also provide a heuristic search algorithm that converges on the optimal decomposition. Restricting the decomposition to some specific types of local behaviors reduces significantly the complexity of planning. In particular, we present a polynomial-time algorithm for the case in which individual agents perform goal-oriented behaviors between communications. The paper concludes with an additional tractable algorithm that enables the introduction of human knowledge, thereby reducing the overall problem to finding the best time to communicate. Empirical results show that these approaches provide good approximate solutions.

In this article we consider the issue of optimal control in collaborative multi-agent systems with stochastic dynamics. The agents have a joint task in which they have to reach a number of target states. The dynamics of the agents contains additive control and additive noise, and the autonomous part factorizes over the agents. Full observation of the global state is assumed. The goal is to minimize the accumulated joint cost, which consists of integrated instantaneous costs and a joint end cost. The joint end cost expresses the joint task of the agents. The instantaneous costs are quadratic in the control and factorize over the agents. The optimal control is given as a weighted linear combination of single-agent to single-target controls. The single-agent to single-target controls are expressed in terms of diffusion processes. These controls, when not closed form expressions, are formulated in terms of path integrals, which are calculated approximately by Metropolis-Hastings sampling. The weights in the control are interpreted as marginals of a joint distribution over agent to target assignments. The structure of the latter is represented by a graphical model, and the marginals are obtained by graphical model inference. Exact inference of the graphical model will break down in large systems, and so approximate inference methods are needed. We use naive mean field approximation and belief propagation to approximate the optimal control in systems with linear dynamics. We compare the approximate inference methods with the exact solution, and we show that they can accurately compute the optimal control. Finally, we demonstrate the control method in multi-agent systems with nonlinear dynamics consisting of up to 80 agents that have to reach an equal number of target states.