A Bottom-Up Model of Skill Learning.pdf

A Bottom-Up Model of Skill Learning Ron Sun (rsun@cs.ua.edu) Edward Merrill (emerrill@gp.as.ua.edu) Todd Peterson (todd@cs.ua.edu) The University of Alabama Tuscaloosa, AL 35487 Abstract We present a skill learning model CLARION. Different from existing models of high-level skill learning that use a top- down approach (that is, turning declarative knowledge into procedural knowledge), we adopt a bottom-up approach to- ward low-level skill learning, where procedural knowledge de- velops first and declarative knowledge develops later. CLAR- ION is formed by integrating connectionist, reinforcement, and symbolic learning methods to perform on-line learning. We compare the model with human data in a minefield navigation task. A match between the model and human data is found in several respects. Introduction The acquisition and use of skill constitute a major portion of human activities. Skills vary in complexity and degree of cognitive involvement. They range from simple motor movements and other routine tasks in everyday activities to high-level intellectual skills. We study “lower-level” cogni- tive skills, which have not received sufficient research atten- tion. One type of task that exemplifies what we call low-level cognitive skill is reactive sequential decision making (Sun et al 1996). It involves an agent selecting and performing a se- quence of actions to accomplish an objective on the basis of moment-to-moment information (hence the term “reactive”). An example of this kind of task is the minefield navigation task developed at The Naval Research Lab (see Gordon et al. 1994). This kind of task setting appears to tap into real-world skills associated with decision making under conditions of time pressure and limited information. Thus, the results we obtain from human experiments will likely be transferable to real-world skill learning situations. Yet this kind of task is suitable for computational modeling given the recent de- velopment of machine learning tech