Matthew Taylor

taylorm@lafayette.edu

Assistant Professor
Department of Computer Science
Lafayette College
Easton, PA 18042

Office:
Acopian Engineering Center, room 522
610-330-5417





Publications       Bio       Teaching       CV       Research       Code       Links




News


AAMAS-12 was particularly competitive this year but we had two papers accepted!
  • Reinforcement learning transfer via sparse coding. Haitham Bou Ammar, Karl Tuyls, Matthew E. Taylor, Kurt Driessen, and Gerhard Weiss. (Full Paper)
  • Towards student/teacher learning in sequential decision tasks. Lisa Torrey and Matthew E. Taylor. (Extended Abstract)
Additionally, we'll present two papers at the ALA workshop at AAMAS.
  • An Empirical Analysis of RL's Drift From Its Behaviorism Roots. Matthew Adams, Robert Loftin, Matthew E. Taylor, Michael Littman and David Roberts. (Long Oral Presentation)
  • Help an Agent Out: Student/Teacher Learning in Sequential Decision Tasks. Lisa Torrey and Matthew E. Taylor. (Long Oral Presentation)



Brief Biography

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.



Teaching

Spring 2012
CS106: Personal Robotics
VAST200: Computers and Society
 

Fall 2011
CS203: Computer Organization
CS420: Artificial Intelligence
 
Spring 2011
CS102: Principles of CS I (see Moodle site)
 
Fall 2010
CS203: Computer Organization
CS414: Introduction to Machine Learning



CV

View my CV as:
pdf or ps.

Where I've been in pictures:


Research

I have worked with Milind Tambe as part of the TEAMCORE research group and am also a former member of the Learning Agents Research Group, directed by Peter Stone.

My research focuses on agents, physical or virtual entities that interact with their environments. My main goals are to enable individual agents, and teams of agents, to

  1. learn tasks in real world environments that are not fully known when the agents are designed;
  2. perform multiple tasks, rather than just a single task; and
  3. allow agents to robustly coordinate with, and reason about, other agents.
Additionally, I am interested in exploring how agents can learn from humans, whether the human is explicitly teaching the agent, the agent is passively observing the human, or the agent is actively cooperating with the human on a task.

A selection of current and past research projects follows.

Transfer Learning  

Transfer Learning

My dissertation focused on leveraging knowledge from a previous task to speed up learning in a novel task, focusing on reinforcement learning domains.
I gave a talk at AGI-08 that gives a brief introduction to, and motivation for, transfer learning.

Representative Publication:
Transfer Learning via Inter-Task Mappings for Temporal Difference Learning (JMLR-07)
Full list of relevant publications
 
RL Agent  

Reinforcement Learning

Much of my graduate work centered on reinforcement learning (RL) tasks, where agents learn to perform (initially) unknown tasks by optimizing a scalar reward. RL is well suited to allowing both virtual and physical agents to learn when humans are unable (or unwilling) to design optimal solutions themselves.

Representative Publication
Critical Factors in the Empirical Performance of Temporal Difference and Evolutionary Methods for Reinforcement Learning (JAAMAS-09)
Full list of relevant publications
 
Exploration/Exploitation
 

Multi-agent Exploration and Optimization

Since coming to USC, one of the most exciting projects we have worked on is a version of Distributed Constraint Optimization Problem (DCOP) where the agents have unknown rewards. This may also be thought of as a multi-agent, multi-armed bandit. This problem is relevant for tasks that require coordination under uncertainty, such as in wireless sensor networks.

Representative Publication
DCOPs Meet the Real World: Exploring Unknown Reward Matrices with Applications to Mobile Sensor Networks (IJCAI-09)
Full list of relevant publications
 

Code



Links