SOAR extends upon previous approaches to ANN search, such as spill trees, that utilize multiple redundant representations while partitioning the data to reduce the probability of missing a nearest neighbor during search. Rather than training and computing these redundant representations independently, however, SOAR uses an loss, which optimizes each representation to compensate for cases where other representations perform poorly. This drastically improves the overall index quality, resulting in state-of-the-art ANN benchmark performance while maintaining fast indexing times and low memory consumption.

However, I believe that the distinction of "neats" and "scruffies" raised at Cog Sci in '81 didn't define scruffies as people who built expert systems [they didn't really exist as a "real" part of MAD. Instead, I believe AI These are the researchers who read Hawkings and say "gee, if his model of the lo-23 second big bang is right, then the distribution of intergalactic gases should be relatively even. Let's go see if that's true. However, to run our experiments we'll need a more sensitive space-based sensing device, so let's work with the engineers to design one." I think one could make the case (although not from the data collected in Cohen's survey) that the two methodologies are not informed and influenced by each other to the extent they should or could be.

This article describes requirements for synthetic adversaries for urban combat training and a prototype application, MOUTBots. MOUTBots use a commercial computer game to define, implement, and test basic behavior representation requirements and the Soar architecture as the engine for knowledge representation and execution. The article describes how these components aided the development of the prototype and presents an initial evaluation against competence, taskability, fidelity, variability, transparency, and efficiency requirements. Urban combat is characterized by building-to-building, room-to-room fighting. Frequent training is an essential element in reducing casualties.

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 project is aimed at developing humanlike, intelligent agents that can interact with each other, as well as with humans, in such virtual environments. Our current target is intelligent automated pilots for battlefield-simulation environments. These dynamic, interactive, multiagent environments pose interesting challenges for research on specialized agent capabilities as well as on the integration of these capabilities in the development of "complete" pilot agents. We are addressing these challenges through development of a pilot agent, ...

It is the ultimate scientific question underlying psychology and AI as well as a substantial part of philosophy: What is the nature of the mind? Newell's autobiography (American Psychological Association 1986) puts it thusly: The central line of Newell's research has remained always the quest for understanding the nature of the mind. The detailed analysis of protocols, the development of production systems, pulling together the theory of human problem solving (in the book of the same name, with Herb Simon), the development of the notion of cognitive architecture, the problem-space hypothesis, a theory of how humans acquire cognitive skills, work on artificial intelligence systems for doing demanding intellectual tasks (such as discovering algorithms), the development of a complete architecture for intelligence--these are some of the main stepping stones. They comprise various mixtures of artificial intelligence and cognitive psychology, as chance and opportunity would have it. This central question will occupy Newell for the rest of his research life, no doubt.

A recurring requirement for human-level artificial intelligence is the incorporation of vast amounts of knowledge into a software agent that can use the knowledge in an efficient and organized fashion. This article discusses representations and processes for agents and behavior models that integrate large, diverse knowledge stores, are long-lived, and exhibit high degrees of competence and flexibility while interacting with complex environments. There are many different approaches to building such agents, and understanding the important commonalities and differences between approaches is often difficult. We introduce a new approach to comparing frameworks based on the notions of commitment, reconsideration, and a categorization of representations and processes. We review four agent frameworks, concentrating on the major representations and processes each directly supports.

TACAIR-SOAR flew all U.S. fixed-wing aircraft. The general goal was to generate behavior that "looks human" when viewed by a training audience participating in operational military exercises. Its most dramatic use was in the Synthetic Theater of War 1997 (STOW '97), held 29-31 October 1997 (Ceranowicz, 1998; Laird, Jones, and Nielsen 1998; Laird et al. 1998). STOW '97 was a United States Department of Defense (DoD) Advanced Concept Technology Demonstration (ACTD) that was integrated with the United Endeavor 98-1 (UE 98-1) training exercise. As an ACTD, the overall goal of STOW '97 was to permit an early and inexpensive evaluation of advanced technologies that show promise for improving military effectiveness.

This article shows how tools to create intelligent agents can be improved by taking advantage of established software-engineering principles such as high-level languages, maintenance-oriented development environments, and software reuse. We describe how these principles have been realized in the Herbal integrated development environment, a collection of tools that allows agent developers to exploit modern software-engineering principles. We present an example integrated agent development environment that realizes these principles and provides lessons for other agent architectures, both existing and in development. Creating complex software is not a new problem, and the software-engineering community has developed principles to guide solving complex problems with software. Developing intelligent agents is a complex software-engineering activity but the benefits of applying software-engineering principles such as high-level languages, maintenance-oriented development environments, and software reuse to intelligent agent development have not yet fully migrated to the agent-development community.

They are held on a Saturday and Sunday, with a tutorial or two on the preceding Friday. This year the workshop was preceded by two days of tutorials: an introductory tutorial on Thursday and a more advanced tutorial on Friday. The tutorials were held at the University of Michigan's Advanced Technology Lab and at the workshop site. There were 37 talks this year as well as a discussion session with 57 attendees. Seven sites made one presentation, sometimes involving multiple researchers.

ISIS's development was driven by the C4.5, ISIS players learned offline to STEAM's teamwork reasoning is currently However, the RoboCup simulator will evolve for RoboCup-98 toward more humanlike play.