dylanashley
PhD student studying reinforcement learning with Jürgen Schmidhuber. MSc with Richard Sutton at the University of Alberta. Sometimes amateur photographer.
Pinned Repositories
tea-time-talks
The source code for the tea time talks web page.
catastrophic-forgetting
Source code for the experiments in my MSc thesis titled Understanding Forgetting in Artificial Neural Networks.
curriculum-vitae
The source code for my curriculum vitae.
direct-lambda-greedy
A comparison of online variance estimation methods for Reinforcement Learning in a Horde architecture.
dylanashley.github.io
The source code for my personal website.
obfuscate
A demonstration of a simple hack to hide a file inside an image file.
outlier-based-exploration
A look into the potential of using Local Outlier Factors from Unsupervised Learning as a way of guiding exploration in a Reinforcement Learning Agent.
reward-weighted-regression
story-distiller
variance-learning
Some material relating to the paper Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return.
dylanashley's Repositories
dylanashley/story-distiller
dylanashley/catastrophic-forgetting
Source code for the experiments in my MSc thesis titled Understanding Forgetting in Artificial Neural Networks.
dylanashley/reward-weighted-regression
dylanashley/automatic-album-sequencing
dylanashley/variance-learning
Some material relating to the paper Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return.
dylanashley/curriculum-vitae
The source code for my curriculum vitae.
dylanashley/direct-lambda-greedy
A comparison of online variance estimation methods for Reinforcement Learning in a Horde architecture.
dylanashley/dylanashley.github.io
The source code for my personal website.
dylanashley/obfuscate
A demonstration of a simple hack to hide a file inside an image file.
dylanashley/outlier-based-exploration
A look into the potential of using Local Outlier Factors from Unsupervised Learning as a way of guiding exploration in a Reinforcement Learning Agent.
dylanashley/playlist-story-builder
Embeds a story into a music playlist by sorting the playlist so that the order of the music follows a narrative arc.
dylanashley/programming-problems
A collection of solutions to some competitive programming problems.
dylanashley/robot-limb-testai
dylanashley/story-template-extraction
Extracts a set of narrative arc templates from albums in the Free Music Archive dataset.