Anna Hakhverdyan
Anna Hakhverdyan Աննա Հախվերդյան

MSc in Computing Science

University of Alberta

I am a Research Assistant at the University of Alberta working with Martha White. I have completed my MSc degree in Computing Science under the supervision of Martha White in the RLAI Lab. Prior to that, I obtained a BSc from the National Polytechnic University of Armenia (NPUA) in Information Technologies (IT).

My current research is focused on online reinforcement learning, particularly on designing adaptable agents that can learn tasks robustly, even as their surroundings change. In my MSc thesis, I explored how adjusting various hyperparameters could enhance this adaptability.

Lately, I’ve become increasingly interested in the concept of agents that are aware of their limitations - whether computational or otherwise - and capable of recognizing and adapting to changes they’ve made in their surroundings. I believe this self-awareness could help with more efficient learning and the emergence of agency. Ultimately, my goal is to develop methods compelling enough to attract interest from psychologists to study agent behaviors.

Contact: hakhverd [at] ualberta [dot] ca

Download CV
Interests
  • Continual Reinforcement Learning
  • Single-lifetime agents
  • Robust Learning
  • Resource-constrained Learning
Education
  • MSc in Computing Science

    University of Alberta

  • BSc in Information Technologies

    National Polytechnic University of Armenia

Publications
(2022). NS3: Neuro-symbolic Semantic Code Search. In NeurIPS'22.

Experience

  1. Research Assistant

    University of Alberta - RLAI Lab

    Responsibilities include:

    • Finishing up my thesis work for journal submission.
    • Developing a suite of environments for process control.
    • Working on developing environments suitable for Continual learning.
    • Understanding and evaluating RL agents in curated animal learning experiments.
  2. Machine Learning Engineer

    Magical Labs

    Responsibilities include:

    • Developed models and pipelines for autonomous vehicle control.
    • Worked on compressing large neural networks with RL agents for mobile integration.
  3. Machine Learning Engineer

    Perpetuum Motors

    Responsibilities include:

    • Conducted research on developing an end-to-end autonomous driving pipeline for simulated games.
  4. Software Engineer

    ForgeFiction

    Responsibilities include:

    • Developed and designed API requests and database architectures.
    • Optimized the application for maximum speed and scalability.

Education

  1. MSc in Computing Science

    University of Alberta

    GPA: 3.8/4.0

    My Master’s thesis explores online hyperparameter tuning in reinforcement learning, where an agent adapts its hyperparameters during interactions rather than relying on a pre-tuning phase.

  2. BSc in Information Technologies

    National Polytechnic University of Armenia
    GPA: 3.92/4.0
Technical Skills and Hobbies
Python
Bash, Version Control
SQL, NoSQL
Jax, PyTorch, Numpy
Reading
Photography
Cooking
Languages
100%
Armenian
95%
English
95%
Russian
60%
Japanese
40%
Korean