Matthew Taylor

Postdoctoral Research Associate
Department of Computer Science
The University of Southern California
Los Angeles, CA 90089

Publications       Bio       CV       Research       Teaching       Links


I have recently accepted a position as assistant professor at Lafayette College in the
computer science department, starting this summer.
At AAMAS-10 in Toronto:
At AAAI-10 in Atlanta, I'll be presenting our Nectar Track paper: Evolving Compiler Heuristics to Manage Communication and Contention by Taylor, Coons, Robatmili, Maher, Burger, and McKinley.

Brief Biography

Matthew E. Taylor is a postdoctoral research associate at the University of Southern California with Milind Tambe. He 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. Current research interests include multi-agent systems, reinforcement learning, and transfer learning.


View my CV as:
pdf or ps.

Where I've been in pictures:


I currently work with Milind Tambe as part of the TEAMCORE research group and am 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

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
Use-based ML  

Use-Based Machine Learning

I am also interested in applying machine learning techniques to problems not explicitly designed by machine learning specialists. Put differently, I want to improve learning algorithms so that they are more useful in real-world situations and usable by non-specialists.

Representative Publication
Feature Selection and Policy Optimization for Distributed Instruction Placement Using Reinforcement Learning (PACT-08)
Full list of relevant publications

Multi-Agent Planning Under Uncertainty

Distributed Partially Observable Markov Decision Processes (DEC-POMDPs) are a powerful formalism for allowing multiple agent/robots to plan in real world domains. However, the computational complexity of current techniques must be significantly reduced in order for algorithms to be sufficiently fast for real-world applications.

Representative Publication
Exploiting Coordination Locales in Distributed POMDPs via Social Model Shaping (ICAPS-09)
Full list of relevant publications
An ARMOR Checkpoint  

Game Theory for Security Applications

Game theory has been an important component of deployed security applications, such as the ARMOR project at the Los Angeles International Airport. I have worked to evaluate one such project, helping to verify that game theoretic principals still apply in the deployed, real world, application.

Representative Publication
A Framework for Evaluating Deployed Security Systems: Is There a Chink in your ARMOR? (Informatica-10)
Full list of relevant publications
Example Massive Image  

Crowd Evacuation Simulation

Agent-based modeling of large-scale crowds has the potential to help plan building layouts, assist with security and disaster response training, and estimate the impact of different disasters. In collaboration with Massive Software, the LAX police, and the USC School of Cinema, we aim to create psychologically and physically plausable simulations of hundreds of agents with movie-quality visualization.
Representative Publication
Agent-based Evacuation Modeling: Simulating the Los Angeles International Airport (EMWS-09)


I am currently focusing on research during my post-doc. I was an undergraduate TA and tutor for both computer science and physics at
Amherst College. As a graduate student, I was a TA for Computer Fluency for one semester with Bruce Porter. In the Fall of 2007 and the Spring of 2008 I taught cs 108, Introduction to Linux.