BYU CS Logo
Computing That Serves

Towards Real-Life Reinforcement Learning

Date: 

Thursday, February 17, 2005 - 10:00am

Speaker: 

Michael Littman, Director of the Rutgers Laboratory for Real Life-Reinforcement Learning

The reinforcement-learning hypothesis is that intelligent behavior arises from the actions of an individual seeking to maximize its received reward signals in a complex and changing world. This perspective suggests a research program with the goal of understanding where reward signals come from and developing algorithms that search the space of behaviors to maximize reward signals.  In the past 15 years, great strides have been made in understanding models and algorithms for reward optimization.  I will survey some of this work, and suggest what advances in understanding will be needed to build successful learners in real-life environments.

Biography: 

Michael Littman is director of the Rutgers Laboratory for Real-Life Reinforcement Learning (RL3) and his research in machine learning examines algorithms for decision making under uncertainty.  After earning his Ph.D. from Brown University in 1996, Michael worked as an assistant professor at Duke University, a member of technical staff in AT&T's AI Principles Research Department, and is now an associate professor of computer science at Rutgers.  He is on the executive council of the American Association for AI, an advisory board member of the Journal of AI Research and an action editor of the Journal of Machine Learning Research.




Academics