Intrinsically Motivated Reinforcement Learning: A Promising Framework For Developmental Robot Learning

Andrew Stout
George D. Konidaris
Andrew G. Barto

Article comments

This paper was harvested from CiteSeer

Abstract

One of the primary challenges of developmental robotics is the question of how to learn and represent increasingly complex behavior in a self-motivated, open-ended way. Barto, Singh, and Chentanez (Barto, Singh, & Chentanez 2004; Singh, Barto, & Chentanez 2004) have recently presented an algorithm for intrinsically motivated reinforcement learning that strives to achieve broad competence in an environment in a tasknonspecific manner by incorporating internal reward to build a hierarchical collection of skills. This paper suggests that with its emphasis on task-general, self-motivated, and hierarchical learning, intrinsically motivated reinforcement learning is an obvious choice for organizing behavior in developmental robotics. We present additional preliminary results from a gridworld abstraction of a robot environment and advocate a layered learning architecture for applying the algorithm on a physically embodied system.