This decommissioned ERA site remains active temporarily to support our final migration steps to https://ualberta.scholaris.ca, ERA's new home. All new collections and items, including Spring 2025 theses, are at that site. For assistance, please contact erahelp@ualberta.ca.
Theses and Dissertations
This collection contains theses and dissertations of graduate students of the University of Alberta. The collection contains a very large number of theses electronically available that were granted from 1947 to 2009, 90% of theses granted from 2009-2014, and 100% of theses granted from April 2014 to the present (as long as the theses are not under temporary embargo by agreement with the Faculty of Graduate and Postdoctoral Studies). IMPORTANT NOTE: To conduct a comprehensive search of all UofA theses granted and in University of Alberta Libraries collections, search the library catalogue at www.library.ualberta.ca - you may search by Author, Title, Keyword, or search by Department.
To retrieve all theses and dissertations associated with a specific department from the library catalogue, choose 'Advanced' and keyword search "university of alberta dept of english" OR "university of alberta department of english" (for example). Past graduates who wish to have their thesis or dissertation added to this collection can contact us at erahelp@ualberta.ca.
Items in this Collection
- 30White, Martha (Computing Science)
- 5White, Adam (Computing Science)
- 1Bowling, Michael (Computing Science)
- 1Cutkosky, Ashok (Electrical and Computer Engineering)
- 1Farahmand, Amir-massoud (Computer Science, University of Toronto)
- 1Fyshe, Alona (Computing Science)
- 13Reinforcement Learning
- 7Machine Learning
- 3Neural Networks
- 3Reinforcement learning
- 2Continual Learning
- 2Dyna
-
Fall 2023
We study the use of reinforcement-learning based prediction approaches for a real drinking-water treatment plant. Developing such a prediction system is a critical step on the path to optimizing and automating water treatment. Before that, there are many questions to answer about predictability...
-
Fall 2024
Classical wisdom in machine learning advises controlling the complexity of the hypothesis space for achieving good generalization. Despite this, modern overparametrized neural networks demonstrate remarkably high generalization performance, oftentimes with larger and more expressive architectures...
-
Spring 2020
In model-based reinforcement learning, planning with an imperfect model of the environment has the potential to harm learning progress. But even when a model is imperfect, it may still contain information that is useful for planning. In this thesis, we investigate the idea of using an imperfect...
-
Fall 2020
For artificially intelligent learning systems to be deployed widely in real-world settings, it is important that they be able to operate decentrally. Unfortunately, decentralized control is challenging. Even finding approximately optimal joint policies of decentralized partially observable Markov...
-
Strange springs in many dimensions: how parametric resonance can explain divergence under covariate shift.
DownloadFall 2021
Most convergence guarantees for stochastic gradient descent with momentum (SGDm) rely on independently and identically ditributed (iid) data sampling. Yet, SGDm is often used outside this regime, in settings with temporally correlated inputs such as continual learning and reinforcement learning....
-
Fall 2021
Structural credit assignment in neural networks is a long-standing problem, with a variety of alternatives to backpropagation proposed to allow for local training of nodes. One of the early strategies was to treat each node as an agent and use a reinforcement learning method called REINFORCE to...
-
Towards Practical Offline Reinforcement Learning: Sample Efficient Policy Selection and Evaluation
DownloadSpring 2024
Offline reinforcement learning (RL) involves learning policies from datasets, rather than online interaction. The dissertation first investigates a critical component in offline RL: offline policy selection (OPS). Given that most offline RL algorithms require careful hyperparameter tuning, we...
-
Spring 2024
Optimistic value estimates provide one mechanism for directed exploration in reinforcement learning (RL). The agent acts greedily with respect to an estimate of the value plus what can be seen as a value bonus. The value bonus can be learned by estimating a value function on reward bonuses,...
-
Fall 2019
In this thesis, we investigate different vector step-size adaptation approaches for continual, online prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad,...
-
Fall 2023
Oftentimes, machine learning applications using neural networks involve solving discrete optimization problems, such as in pruning, parameter-isolation-based continual learning and training of binary networks. Still, these discrete problems are combinatorial in nature and are also not amenable to...