Abstract:

Using computers to provide personalized instruction as an alternative to human tutors has drawn the attention of researchers in the fields of computer science, education, psychology and cognitive science. Thanks to their cooperative efforts, we have Intelligent Tutoring Systems (ITSs), embodying the computer-as-tutor paradigm. The agent paradigm now allows researchers to collaborate effectively in an effort to develop efficient user-centered learning environments.
Video games have gained much attention in recent years in education due to their ability to engage users. But, in most video games, the knowledge about how the systems work is not exposed for users to reflect upon. This is because, once all the tricks are exposed, a game will lose its motivational factor. Users will soon get bored in a transparent environment where there is nothing mysterious to explore. We would like our learning environment to be transparent as well as motivational. To make it transparent, we need to develop tools for users to construct knowledge to be passed to the users.

The primary goal of this dissertation is to research, design, and prototype an intelligent reflective agent situated in an educational gaming environment based on a cognitive framework, called REAL (Reflective Agent Learning Environment). Attempts were made to encourage reflective thinking by having users explicitly externalize their internal knowledge representations, applying them in a simulation game, which, ideally, generates a sequence of behaviors analogous to those generated by the users’ imaginary worlds. It is our hope that when users begin to recognize relationships between existing knowledge and newly presented meanings, learning occurs, thus making the new information accessible as part of the learners’ active reservoirs of knowledge. The tangible results of this research are some prototypes of the REAL applications.

We focused on system design for REAL Planet. The time and efforts on its design paid off when we started to design REAL Business, which took two developer weeks of programming to get built. The external evaluation of REAL aims at testing the usefulness of the REAL system for the user, such as its ability to foster learning, motivate learners, and encourage scientific exploration. The evaluation of the learning outcome is not a focus in this study. Lessons derived from the process are intended to be used for the design of specific REAL applications and studies in the future. The result of the evaluations reveals the educational impact and value of REAL and will therefore influence the direction for the future research and development.

From the design and study on the REAL applications, we found the following value for REAL as a cognitive framework. (1) The learning environment is motivational. (2) The REAL framework is reusable and extensible. (3) The REAL platform encourages collaboration among researchers with interest in such areas as artificial intelligence, intelligent computer-aided instruction, human computer interaction, human cognition, and educational games, to name a few. It can serve as a generic platform for those researchers to embed their ideas and test out their hypotheses.

Keywords:

.