Timothy M. Converse

Learn More
In planning and activity research there are two common approaches to matching agents with environments. Either the agent is designed with a specific environment in mind, or it is provided with learning capabilities so that it can adapt to the environment it is placed in. In this paper we look at a third and underexploited alternative: designing agents which(More)
This paper presents an outline of a theory of agency that seeks to integrate ongoing understanding, planning ng and activity into a single model of representation and processing. Our model of agency rises out of three basic pieces of work: Schank's structural model of memory organization (Schank, 1982), Hammond's work in case-based planning and dependency(More)
There is a tension in the world between complexity and simplicity. On one hand, we are faced with a richness of environment and experience that is at times overwhelming. On the other, we seem to be able to cope and even thrive within this complexity through the use of simple scripts, stereotypical judgements, and habitual behaviors. In order to function in(More)
In earlier work (Hammond 1986), we proposed a mechanism for learning from execution-time plan failure. In this paper, we suggest a corollary notion of learning from execution-time planning opportunities. We argue that both are special cases of learning from expectation failure (Schank 1982). The result of this type of learning is a set of plans for(More)
Interest in psychological experimentation from the Artificial Intelligence community often takes the form of rigorous post-hoc evaluation of completed computer models. Through an example of our own collaborative research, we advocate a different view of how psychology and AI may be mutually relevant, and propose an integrated approach to the study of(More)
  • 1