Search

Fall 2009

Waugh, Kevin

For zero-sum games, we have efficient solution techniques. Unfortunately, there are interesting games that are too large to solve. Here, a popular approach is to solve an abstract game that models the original game. We assume that more accurate the abstract games result in stronger strategies....

Spring 2010

White, Martha

In this work, we present a unified, general approach to variance reduction in agent evaluation using machine learning to minimize variance. Evaluating an agent's performance in a stochastic setting is necessary for agent development, scientific evaluation, and competitions. Traditionally,...

Spring 2013

Afkanpour, Arash

Multiple kernel learning (MKL) addresses the problem of learning the kernel function from data. Since a kernel function is associated with an underlying feature space, MKL can be considered as a systematic approach to feature selection. Many of the existing MKL algorithms perform kernel learning...

Fall 2013

Gendron-Bellemare, Marc

This thesis presents new algorithms for dealing with large scale reinforcement learning problems. Central to this work is the Atari 2600 platform, which acts as both a rich evaluation framework and a source of challenges for existing reinforcement learning methods. Three contributions are...

Fall 2013

Vafadost, Mostafa

Given nothing but the generative model of the environment, Monte Carlo Tree Search techniques have recently shown spectacular results on domains previously thought to be intractable. In this thesis we try to develop generic techniques for temporal abstraction inside MCTS that would allow the...

Spring 2014

Davidson, Joshua

Efficient, unbiased estimation of agent performance is essential for drawing statistically significant conclusions in multi-agent domains with high outcome variance. Naive Monte Carlo estimation is often insufficient, as it can require a prohibitive number of samples, especially when evaluating...

Spring 2015

Das Gupta, Ujjwal

Much of the focus on finding good representations in reinforcement learning has been on learning complex non-linear predictors of value. Methods like policy gradient, that do not learn a value function and instead directly represent policy, often need fewer parameters to learn good policies....

Spring 2015

Rayner, David Christopher Ferguson

Heuristic search is a central problem in artificial intelligence. Among its defining properties is the use of a heuristic, a scalar function mapping pairs of states to an estimate of the actual distance between them. Accurate heuristics are generally correlated with faster query resolution and...

Fall 2015

Davis, Trevor

Extensive-form games are a powerful framework for modeling sequential multi-agent interactions. In extensive-form games with imperfect information, Nash equilibria are generally used as a solution concept, but computing a Nash equilibrium can be intractable in large games. Instead, a variety of...

Spring 2015

White, Martha

This dissertation explores regularized factor models as a simple unification of machine learn- ing problems, with a focus on algorithmic development within this known formalism. The main contributions are (1) the development of generic, efficient algorithms for a subclass of regularized...