My program of research is an interdisciplinary study of mechanisms and algorithms permitting systems—both natural and artificial—to improve performance with experience, that is, to learn. I direct the Autonomous Learning Laboratory in the Department of Computer Science, which focuses on learning in both machines and animals. We are a highly interdisciplinary lab, interacting with researchers in psychology, neuroscience, control engineering, operations research, and robotics. We are best known for pioneering work in Reinforcement Learning. This is a framework for learning to maximize reward over time while interacting with a dynamic environment. We also work on neural models of animal motor learning, maintaining close contact with the laboratory of Prof. John Moore, and on the development of motor control abilities by infants in collaboration with Profs. Neil Berthier and Rachel Keen. Biological control systems demonstrate an amazing ability to deal with complex and ever-changing bodies and environments.
Articles
Other
An Intrinsic Reward Mechanism for Efficient Exploration (with Özgür Şimşek), Computer Science Department Faculty Publication Series (2006)
How should a reinforcement learning agent act if its sole purpose is to efficiently learn...
Socially Guided Machine Learning (with Andrea Lockerd Thomaz, Cynthia Breazeal, and Rosalind Picard), Computer Science Department Faculty Publication Series (2006)
Social interaction will be key to enabling robots and machines in general to learn new...
Identifying Useful Subgoals in Reinforcement Learning by Local Graph Partitioning (with Özgür Şimşek and Alicia P. Wolfe), Computer Science Department Faculty Publication Series (2005)
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our...
Intrinsically Motivated Reinforcement Learning: A Promising Framework For Developmental Robot Learning (with Andrew Stout and George D. Konidaris), Computer Science Department Faculty Publication Series (2005)
One of the primary challenges of developmental robotics is the question of how to learn...
Using Relative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning (with Özgür Şimşek), Computer Science Department Faculty Publication Series (2004)
We present a new method for automatically creating useful temporal abstractions in reinforcement learning. We...