I have a PhD in Computer Science from the University of Texas in Austin, focused on machine learning and robotics. My bachelor's degree is in computer engineering from Northeastern University in Boston. I was born in Chicago and grew up in Wrentham, Massachusetts.Intelligence and learning fascinate me and I am researching reinforcement learning and robotics. For more info on my research interests, see below or check out this page.
This is a website I first designed in college in 2000. There is a lot of old content on here such as random photos, stories, quotes, and projects. My rantings has any random thoughts of mine on various topics and the Patriots blog has my thoughts on the New England Patriots. I also have worked on lots of various projects of my own including an online chatbot, designing my own robot from scratch, writing a program to play a 3D version of the classic game Connect Four, writing a program to predict the scores of NFL football games, and trying to write a program to play poker. The sections below highlight some of the better parts of the website. Enjoy!!
My research is in two areas: reinforcement learning and robot soccer. Reinforcement learning is a type of learning algorithm which allows an agent to learn through interaction with its environment. In robot soccer, we program robots to play soccer autonomously, forcing us to address the issues faced by robotics in general. I am a member of the UT Austin Villa Robot Soccer team, which won the 2012 Standard Platform League World Championship. I worked on all parts of the code, including vision, localization, locomotion, and behaviors. Check out our highlight videos here or below! My research in reinforcement learning looks at ways to extend model-based reinforcement learning methods to work in larger domains, as well as examining the exploration versus exploitation problem. I would like to make curious agents that can quickly learn about the world around them. My goal is to develop such methods so that I can then apply them to robots. For more information on my research, please visit my academic website.
2012 Standard Platform League Final
Video of our 2012 Standard Platform League (SPL) final against B-Human, who had won the last 3 years and had never lost a game. Our team won the SPL world championship for the first time in 2012.
On this site, I have always maintained pages containing my rantings. These include random thoughts and musings of mine on topics including technology, the meaning of life, politics, and the future. I currently have a blog where I post my rantings and I have transferred my old rantings from 2001-2004 to the blog as well. Here is the link to the blog:
Here is the latest entry from my rantings blog:
My research is in the area of reinforcement learning, where an agent is learning to solve a sequential decision making task. In it, the agent takes an action from state, which leads it to some new state and provides it some reward. The outcome of the actions can be noisy or random. For example, when you’re driving your car and you make a decision to take a particular turn, there is some noise in the outcome (you can not predict deterministically what will happen). Instead, there may be construction, traffic, pedestrians, etc which cause your trip down this road to take longer or shorter than you would expect. You can’t predict exactly the number of seconds it will take. However, this randomness, at its core, is really the result of partial observability. Partial observability is where you can only observe some part of the world to make your prediction. In this example, you only have access to what you see at the intersection and the info you get from the internet, radio, tv, and your phone. With this information, you cannot predict the time the road will take precisely and instead there is some noise to it. However, if you knew what every other driver was thinking and the route and timings they would take, along with what the weather would do, what the exact construction plans were, etc, then you could conceivably make this prediction accurately (or a computer could). So you can view this decision making task as having noise or being partially observable. This goes on at all levels, but at some point you would need knowledge of every atom and molecule in the system (which can’t be observed), so its easier to approximate things as being noisy. But as we get better and better at observing such things, we can make more deterministic predictions that consider all the factors that we previously ignored as “noise.”
I am a huge fan of the New England Patriots. I went to every home game but one from 1993-2005. I currently keep a blog of my thoughts and opinions on the Patriots. In addition to that, there are pictures from when I went to the Patriots first Super Bowl victory over the Rams in February 2002 and other games. I also have scores from my NFL Predictor software. Here are the links:
Here is the latest entry from my Patriots blog:
I have plenty of photographs on my site, dating from when I got my first digital camera in 2000. I have lots of photos of my friends and stuff, but also photos of places I've been and things that I thought would make cool pictures. Over time, I've varied where I store my photos, so they're at the separate links below:
I am constantly working on various projects. Most of the projects involve some kind of artificial intelligence, either controlling a robot, predicting NFL football scores, or game-playing AI. The highlight of these projects is a 3D Connect Four game I designed where the computer will look up to 6 moves ahead. This game is available for download here on the website. My robot diary contains every step of the process of designing and building my own robot from scratch. I also wrote a program to try to predict scores of NFL football games based on previous week's stats. Enjoy!