About me

I'm currently a post-doc in the Robot Vision and Learning Lab led by Prof. Florian Shkurti. My research focuses on planning and reinforcement learning with large behavior models, exploring in particular how diffusion policies can be used in the offline setting.

Prior to this, I completed a post-doc in the D3M Lab led by Prof. Scott Sanner, where I developed novel research in automated planning, contributed to the development of the RDDL planning language, developed new software for planning (pyRDDLGym), and co-hosted the probabilistic track of the 2023 International Planning Competition (IPC). I completed my PhD in the department of Mechanical and Industrial Engineering at U of T. My thesis focused on knowledge transfer in deep reinforcement learning, developing novel applications of Bayesian inference and mathematical risk analysis to improve the robustness of transfer. My research has been published in top AI/ML conferences such as NeurIPS, UAI, and ICLR. I also interned at Google DeepMind, and was a post-graduate affiliate of the Vector Institute.

Prior to this, I completed my master's degree (MASc) at U of T, where my thesis focused on the theoretical developments of Thompson sampling applied in queueing and admission control problems with demand uncertainty. I received my Bachelor's degree in Business Administration (BBA) from the Schulich School of Business, graduating with distinction.

I enjoy reading books on cognitive science and play classical piano in my spare time.



  1. University of Toronto


    PhD in Department of Mechanical and Industrial Engineering, thesis on knowledge transfer for reinforcement learning agents.

  2. University of Toronto

    2015 — 2017

    MASc in Operations Research, thesis on online parameter learning in queueing and admission control problems with regret bounds.

  3. Schulich School of Business, York University

    2010 — 2014

    Graduated with distinction with a major in finance.


  1. Post-Doctoral Fellow, RVL Lab

    2024 — Present

    Developing novel research on large behavior models, such as offline evaluation and optimization of diffusion policies.

  2. Post-Doctoral Fellow, D3M Lab


    Developing novel algorithms and software implementations for efficient and scalable planning in high-dimensional spaces, leveraging techniques such as gradient-based (JAX auto-diff) and gradient-free optimization (Gurobi).

  3. Research Scientist Intern, Google Deepmind


    Derived novel solution techniques and algorithms for the never-ending reinforcement learning problem ("small agent operating in a big world").

  4. Post-Graduate Affiliate, Vector Institute

    2020 — 2022

    Awarded for excellence in AI research.

  5. Research Analyst, Russell Investments

    2014 — 2015

    Collected, analyzed and summarized numerical and qualitative data on mutual funds and client portfolios to guide decision-making and strategy. Also wrote macros to automate data preparation and analysis, resulting in much faster turn-around time.

My skills

  • Machine Learning Research
  • Python (sklearn, numPy, pandas, TensorFlow, JAX, etc.)
  • Data Analysis
  • Object-Oriented Design (Java, C++)





        Contact Form