Planning Cases by Change of Representation Language Ralph Bergmann bergmann@informatik.uni-kl.de Wolfgang Wilke wilke@informatik.uni-kl.de Centre for Learning Systems and Applications (LSA) University of Kaiserslautern, P.O.-Box 3049, D-67653 Kaiserslautern, Germany Abstract Abstraction is one of the most promising approaches to improve the performance of problem solvers. In several domains abstraction by dropping sentences of a domain description -- as used in most hierarchical planners -- has proven useful. In this paper we present examples which illustrate significant drawbacks of abstraction by dropping sentences. To overcome these drawbacks, we propose a more general view of abstraction involving the change of representation language. We have developed a new abstraction methodology and a related sound and complete learning algorithm that allows the complete change of representation language of planning cases from concrete to abstract. However, to achieve a powerful change of th...

The origins of the Soar architecture can be traced back to the seminal research of Allen Newell and Herbert Simon on symbol systems, heuristic search, goals, problem spaces, and production systems. Since its official inception in 1982, Soar has evolved through six major releases, as both an AI architecture and as the basis for a unified theory of cognition. This paper traces this evolutionary path, starting with Soar's intellectual roots, and then proceeding through the stages defined by the six major system releases. Each stage is characterized with respect to a hierarchy of four levels of analysis: the knowledge level, the problem space level, the symbolic architecture level, and the implementation level.

To navigate effectively, an autonomous agent must be able to quickly and accurately determine its current location. Given an initial estimate of its position (perhaps based on dead-reckoning) and an image taken of a known environment, our agent first attempts to locate a set of landmarks (real-world objects at known locations), then uses their angular separation to obtain an improved estimate of its current position. Unfortunately, some landmarks may not be visible, or worse, may be confused with other landmarks, resulting in both time wasted in searching for invisible landmarks, and in further errors in the agent's estimate of its position. To address these problems, we propose a method that uses previous experiences to learn a selection function that, given the set of landmarks that might be visible, returns the subset which can reliably be found correctly, and so provide an accurate registration of the agent's position. We use statistical techniques to prove that the learned selecti...

Although most scheduling problems are NP-hard, domain specific techniques perform well in practice but are quite expensive to construct. In adaptive problem-solving, domain specific knowledge is acquired automatically for a general problem solver with a flexible control architecture. In this approach, a learning system explores a space of possible heuristic methods for one well-suited to the eccentricities of the given domain and problem distribution. In this article, we discuss an application of the approach to scheduling satellite communications. Using problem distributions based on actual mission requirements, our approach identifies strategies that not only decrease the amount of CPU time required to produce schedules, but also increase the percentage of problems that are solvable within computational resource limitations. 1. Introduction With the maturation of automated problem-solving research has come grudging abandonment of the search for "the" domain-independent problem solve...

Abstract not found

We address the issue of rational communicative behavior among autonomous intelligent agents that have to make decisions as to what, to whom, and how to communicate. We treat communicative actions as aimed at increasing the efficiency of interaction among agents. We postulate that a rational speaker design a speech act so as to maximally increase the benefit obtained as the result of the interaction. We quantify the gain in the quality of interaction as the expected utility, and we present a framework that allows an agent to compute the expected utility of various communicative actions. Our framework uses the Recursive Modeling Method as the representation of the agent's state of knowledge, including the agent's preferences, abilities and beliefs about the world, as well as the beliefs the agent has about the other agents, the beliefs it has about the other agents ' beliefs, and so on. A decision-theoretic pragmatics of a communicative act can be then defined as the transformation it induces on the agent's state of knowledge about its decision-making situation. This transformation leads to a change in the quality of the interaction, expressed in terms of the benefit to the agent. We analyze decision-theoretic pragmatics of a number of important communicative acts, and investigate their expected utility using examples.

PROTEGE is a metalevel program that generates knowledge-acquisition tools that are based on the method of skeletal-plan refinement. In this paper, we propose a flexible and extensible architecture that allows the problem-solving method to be assembled from more basic methods. In this architecture, we emphasize (1) a uniform view of problem solving at different levels of granularity, (2) an explicit data model that allows construction of complex datatypes from predefined datatypes, and (3) the inclusion of domaindependent control information within a domain-independent problem-solving method. We show how such a model of problem solving can drive the generation of knowledge-acquisition tools.

We adopt the decision-theoretic principle of expected utility maximization as a paradigm for designing autonomous rational agents, and present a framework that uses this paradigm to determine the choice of coordinated action. We endow an agent with a specialized representation that captures the agent's knowledge about the environment and about the other agents, including its knowledge about their states of knowledge, which can include what they know about the other agents, and so on. This reciprocity leads to a recursive nesting of models. Our framework puts forth a representation for the recursive models and, under the assumption that the nesting of models is finite, uses dynamic programming to solve this representation for the agent's rational choice of action. Using a decision-theoretic approach, our work addresses concerns of agent decision-making about coordinated action in unpredictable situations, without imposing upon agents pre-designed prescriptions, or protocols, ...

Abstract not found

A theoretical framework based on the concepts and tools of nonlinear dynamical systems is advanced to account for both the persistent and transitory changes traditionally shown for the learning and development of motor skills. The multiple time scales of change in task outcome over time are interpreted as originating from the system's trajectory on an evolving attractor landscape. Different bifurcations between attractor organizations and transient phenomena can lead to exponential, power law, or S-shaped learning curves. This unified dynamical account of the functions and time scales in motor learning and development offers several new hypotheses for future research on the nature of change in learning theory. Motor learning and development are characterized by the persistent change in behavior over time. ' There are potentially many indices of change in motor behavior and many time scales over which the change in behavior occurs. Nevertheless, theories of motor learning and development have been predicated predominantly on attempts to determine a single function of behavioral change across a range of task outcomes and context domains. This approach has helped support claims for a general law of learning for the motor and cognitive domains (Mazur & Hastie, 1978; A. Newell & Rosenbloom, 1981; Snoddy, 1926; Thurstone, 1919). The prevailing position on learning curves is that of A. Newell and Rosenbloom, who proposed that the power law is the "ubiquitous law of learning " (p. 2; see also Ivry, 1996; Logan, 1988; Salmoni, 1989). The form of the mathematical function that fits the learning curve is important beyond mere description or curve fitting in that it has been used to support or refute the particular tenets of theories of learning. For example, the power law for behavioral change is a direct consequence of the principles of the chunking theory of learning (A. Newell & Rosenbloom, 1981). However, a number of functions of change other than the power law have been shown in motor learning and development through a century of study (cf.