Search
Skip to Search Results- 21Bowling, Michael (Computing Science)
- 14Schuurmans, Dale (Computing Science)
- 5Szepesvari, Csaba (Computing Science)
- 2Greiner, Russell (Computing Science)
- 1Bellemare, Marc (Google Brain)
- 1Bowling, Mike (Computing Science)
- 9Reinforcement Learning
- 6Artificial Intelligence
- 6Machine Learning
- 6Machine learning
- 3Game Theory
- 2Abstractions
-
Fall 2016
This thesis explores theoretical, computational, and practical aspects of convex (shape-constrained) regression, providing new excess risk upper bounds, a comparison of convex regression techniques with theoretical guarantee, a novel heuristic training algorithm for max-affine representations,...
-
Fall 2019
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure is often the result of specific environmental pressures...
-
Spring 2019
In the reinforcement learning (RL) problem an agent must learn how to act optimally through trial-and-error interactions with a complex, unknown, stochastic environment. The actions taken by the agent influence not just the immediate reward it observes but also the future states and rewards it...
-
Fall 2013
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...
-
Hindsight Rational Learning for Sequential Decision-Making: Foundations and Experimental Applications
DownloadFall 2022
This thesis develops foundations for the development of dependable, scalable reinforcement learning algorithms with strong connections to game theory. I present a version of rationality for learning---one grounded in the learner's experience and connected with the rationality concepts of...
-
Fall 2017
On the one hand, theoretical analyses of machine learning algorithms are typically performed based on various probabilistic assumptions about the data. While these probabilistic assumptions are important in the analyses, it is debatable whether such assumptions actually hold in practice. Another...
-
Fall 2012
This thesis provides a description of the cardiac rhythm as a latent chain of heart sound arrivals which occur over time, where each arrival generates a fixed window of observable data that can be described with arbitrary feature functions. This description of the process produces tractable...
-
Spring 2013
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 2021
The optimization of non-convex objective functions is a topic of central interest in machine learning. Remarkably, it has recently been shown that simple gradient-based optimization can achieve globally optimal solutions in important non-convex problems that arise in machine learning, including...