The goal of this workshop was which was held in June 1995 in San istributed artificial intelligence the cooperative solution of "making connections," trying to better Francisco. The DAI Workshop problems in multiagent intelligent understand the connections received financial support from the systems with both computational between DAI and related fields (for American Association for Artificial and human agents. The central problem example, computer-supported cooperative Intelligence as well as the Boeing in DAI is how to achieve coordinated work, group decision support Company. Registration materials for the Thirteenth National Conference on Artificial Intelligence (AAAI-96), the Eighth Innovative Applications of Artificial Intelligence Conference (IAAI-96), and the Second International Conference on Knowledge Discovery and Data Mining (KDD-96) are now available from the AAAI office at ncai@aaai.org Copies of the AAAI-96 registration brochure are being mailed to all AAAI members.

The goal of the Workshop on Adaptation and Learning in Multiagent Systems was to focus on research that addresses unique requirements for agents learning and adapting to work in the presence of other agents. Recognizing the applicability and limitations of current machine-learning research as applied to multiagent problems and developing new learning and adaptation mechanisms particularly targeted to this class of problems were the primary research issues that we wanted the authors to address. This article outlines the presentations that were made at the workshop and the success of the workshop in meeting the established goals. Issues that need to be better understood are also presented.

This report stems from a workshop that was organized by the Association for the Advancement of Artificial Intelligence (AAAI) and cosponsored by the Information Technology and Organizations Program of the National Science Foundation. The purpose of the workshop was twofold: first, to increase awareness among the artificial intelligence (AI) community of opportunities presented by the National Information Infrastructure (NII) activities, in particular, the Information Infrastructure and Tech-nology Applications (IITA) component of the High Performance Computing and Communications Program; and second, to identify key contributions of research in AI to the NII and IITA.

The Georgia Institute of Technology won the Office Cleanup event at the 1994 AAAI Robot Competition and Exhibition with a multirobot cooperating team. This article describes the design and implementation of these reactive trash-collecting robots, including details of multiagent cooperation, color vision for the detection of perceptual object classes, temporal sequencing of behaviors for task completion, and a language for specifying motor schema-based robot behaviors.

Georgia Tech's approach differed from other The contest required competing by the robots to collect trash; (3) cooperative robot entries to clean up a messy office behaviors provide for cooperation between strewn with trash. Wads of paper, Styrofoam robots; (4) temporal sequencing coordinates coffee cups, and soda cans were placed by transitions between distinct operating states judges throughout the contest arena along for each robot and achieves the desired goal with wastebaskets, where they hoped the state; (5) fast vision locates soda cans, wastebaskets, robots would deposit the trash. During competitive robot hardware and specifies behavioral states trials, each robot was to gather and throw and transitions between them; and (6) a realtime away as much trash as possible in 10 minutes. The task proved processing are outlined in the next section. The article closes trash in a wastebasket. Unfortunately, the with strategies used and lessons learned at the computational overhead was so great that competition. If a robot was The 10-pound robots were built using off-theshelf near an item of trash or a wastebasket, it components at a cost of approximately could signal its intent to pick up or throw $1700 each.

The possibility that the agents the authors make are a little unclear.

The 1994 AAAI Robot-Building Laboratory (RBL-94) was held during the Twelfth National Conference on Artificial Intelligence. The primary goal of RBL-94 was to provide those with little or no robotics experience the opportunity to acquire practical experience in a few days. Thirty persons, with backgrounds ranging from university professors to practitioners from industry, participated in the three-part lab.

In its early stages, the field of AI had as its main goal the invention of computer programs having the general problem-solving abilities of humans. Along the way, a major shift of emphasis developed from general-purpose programs toward performance programs, ones whose competence was highly specialized and limited to particular areas of expertise. In this article, I claim that AI is now at the beginning of another transition, one that will reinvigorate efforts to build programs of general, humanlike competence. These programs will use specialized performance programs as tools, much like humans do.

We study the process of multi-agent reinforcement learning in the context ofload balancing in a distributed system, without use of either centralcoordination or explicit communication. We first define a precise frameworkin which to study adaptive load balancing, important features of which are itsstochastic nature and the purely local information available to individualagents. Given this framework, we show illuminating results on the interplaybetween basic adaptive behavior parameters and their effect on systemefficiency. We then investigate the properties of adaptive load balancing inheterogeneous populations, and address the issue of exploration vs.exploitation in that context. Finally, we show that naive use ofcommunication may not improve, and might even harm system efficiency.

Interactive simulation environments constitute one of today's promising emerging technologies, with applications in areas such as education, manufacturing, entertainment, and training. These environments are also rich domains for building and investigating intelligent automated agents, with requirements for the integration of a variety of agent capabilities but without the costs and demands of low-level perceptual processing or robotic control. Our current target is intelligent automated pilots for battlefield-simulation environments. This article provides an overview of this domain and project by analyzing the challenges that automated pilots face in battlefield simulations, describing how TacAir-Soar is successfully able to address many of them -- TacAir-Soar pilots have already successfully participated in constrained air-combat simulations against expert human pilots -- and discussing the issues involved in resolving the remaining research challenges.