Curricula and Metrics to Investigate Human-Like Learning
Jacob Beal, Paul Robertson, Robert Laddaga · 2009
In order to learn from naive instructors, machines must learn more like how humans learn. We are organizing a “Boot-strapped Learning Cup ” competition, in which competitors attempt to create the best learning agent for a curriculum whose focus is known but whose specifics are not. By focus-ing each competition on a particular factoring of the larger problem of human-like learning, we hope to simultaneously identify productive decompositions of the larger problem and components that can eventually be integrated to solve it. To this end, we seek to measure learner autonomy with “spec-trum curricula ” that measure learning against an incremen-tally varied set of curricula, ranging from extremely tele-graphic to overly detailed. If this program of competitions is successful, it will lead to a