Seminar Series - Real Life Learning Agents

Speaker: Matt Taylor, Department of Computer Science, Lafayette College
Date: Friday, February 17, 2012
Time: 11:15am-12:15pm
Location: 2150 Torgersen

Agents, defined as programs or robots that interact with their environment, are becoming increasingly common. However, the current generation of agents are often unable to robustly interact with each other, or with humans, severely limiting the number of tasks that they can accomplish. Furthermore, these agents typically are unable to adapt to their environment, a critical skill when programmers do not have full knowledge of agents' future environments or when the agents' environment may change over time. This talk will discuss recent work in combining autonomous learning of sequential decision making tasks with transfer learning, a general approach to sharing knowledge between agents with different capabilities, resulting in significant improvements to learning speeds and abilities.

Matthew E. Taylor graduated magna cum laude with a double major in computer science and physics from Amherst College in 2001. After working for two years as a software developer, he began his Ph.D. with a MCD fellowship from the College of Natural Sciences. He received his doctorate from the Department of Computer Sciences at the University of Texas at Austin in the summer of 2008, supervised by Peter Stone. Matt recently completed a two year postdoctoral research position at the University of Southern California with Milind Tambe and is now an assistant professor at Lafayette College in the computer science department. His current research interests include intelligent agents, multi-agent systems, reinforcement learning, and transfer learning.