Skip to content
View tyranitar's full-sized avatar
20 followers · 33 following

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull Sharkx3

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull Sharkx3

Block or report tyranitar

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tyranitar/README.md

👋 Hello there, welcome to my GitHub page

My name is Tyron and I'm the creator of Zetanote. I enjoy the following activities:

  • Training and deploying ML models in the cloud.
  • Getting React to do exactly what I want.
  • Wrangling Docker and Kubernetes.

About me:

  • 🎓 University of Waterloo alum.
  • 👔 Check out my LinkedIn.
  • ✍️ Check out my writing.

🤖 Some reinforcement learning agents that I trained:

Continuous Control Tennis
Continuous control Tennis
AI learning to control its robot arm. AI learning to play tennis against itself.

✨ Some animations that I created for educational purposes:

Continuous Space Discrete Space
Nonlinear animation Daydream animation
A neural network learning to separate data. An RBM daydreaming about handwritten digits.
MLP surface animation Ant colony animation
The output landscape of a neural network as it learns. Simulation of an ant colony gathering food.

🧮 App that I created with my friend Jonathan to help students learn algebra:

Lemma animation

Pinned

  1. the-feynman-journal the-feynman-journal Public

    Source code for visualizations in The Feynman Journal.

    Jupyter Notebook 2

  2. hammock hammock Public

    Forked from quizlet/hammock

    Hammock is a stand-alone mocking library for Hacklang.

    Hack

  3. tennis tennis Public

    Multi-agent reinforcement learning where an agent learns to play tennis against itself. Part of the coursework for Udacity's Deep RL Nanodegree.

    Python 1 1

  4. continuous-control continuous-control Public

    A2C and D4PG implementations for the continuous control challenge. Part of the coursework for Udacity's Deep RL Nanodegree.

    Python 2

  5. generate-faces generate-faces Public

    GAN model for generating celebrity faces. Part of the coursework for Udacity's Deep Learning Nanodegree.

    Jupyter Notebook

  6. ant-colony ant-colony Public

    This is a simulation of an ant colony that demonstrates ant collaboration through the use of pheromone trails.

    MATLAB