• View
• Edit
• History
• Print

Research

Areas of Interest

• Artificial Learning (Learning domains and algorithms, Computational learning theory)
• Biological Learning (Cognitive Science, Computational Neuroscience, Neurophysiology, Developmental Neuroscience)
• Social Learning (Learning in social systems)
• Multiagent Learning
• Robotics (Humanoid and autonomous)
• Scalability (Computational and engineering related)
• Psychological Theories of Learning

Current Research

“Reinforcement learning is a computational approach to understanding and automating goal-directed learning and decision making. It is distinguished from other computational approaches by its emphasis on learning by the individual from direct interaction with the environment, without relying on exemplary supervision or complete models of the environment” - R. Sutton, A. Barto

I’m currently a member of the Autonomous Learning Lab, which works on a subfield of artificial intelligence known as Reinforcement Learning (RL). RL focuses on allowing artificial systems (usually described as Markov Decision Processes) to learn useful behavior given abstract reward signals.

• Intrinsically Motivated Reinforcement Learning
• Models of Motor Control
• Context and Statistical/Episodic Memory in Reinforcement Learning

Additional Topics of Interest:

• Structured Learning
• Developmental Learning
• Neurotransmitter Systems and their effects on learning
• Layered / Multiple Learning Systems (e.g. cerebellum, hippocampus, prefrontal cortex, etc.)

Past Research

• Publications Summary
• Intelligent Robotics Laboratory

Interesting Links:

• Juergen’s Optimal AI

Favorite Robots