Analyzing human's continuous learning processes with the reflection sub task

Abstract

This paper reports our learning support system for a human learner to visualize his/her mental learning processes with invisible mazes for continuous learning. The objective of this research is to bring the learning ability of the learning agent close to that of a human. To fill in the missing piece of reinforcement learning whose learning process is mainly behavior change, we add two mental learning processes, awareness as pre-learning process and reflection as post-learning process. To observe mental learning processes of a human, we propose a new method for visualizing mental learning processes by the reflection subtask with invisible mazes. As the experimental results, there is a strong negative correlation between the number of discovered solutions of the continuous learning task and the reflection cost. It suggests that subjects whose number of discovered solutions is upper do a very good job of the reflection subtask.