Learning and Planning in Markov Environments
Michael L. Littman (Rutgers University)
This tutorial will survey central concepts in single- and multi-agent
decision making for sequential problems. The first half of the
presentation will focus on planning approaches---efficient algorithms
for computing (near) optimal behavior for a variety of different
settings. The second half will turn to learning approaches in which
behavioral decisions are made without an a priori model of the
environment.
Michael Littman is director of the Rutgers Laboratory for Real-Life Reinforcement Learning (RL^3) 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 served on the executive council of the American Association for AI, and is an advisory board member of the Journal of AI Research and an action editor of the Journal of Machine Learning Research.