About me

I recently joined Mesbah Lab at UC Berkeley as a postdoc!

Upper Bound 2024 MPC tutorial: Slides and code here

The broad focus of my work is unifying machine learning and control theory. More specifically, I am keen on alleviating the tension between deep reinforcement learning and model predictive control. A more unified perspective of these two areas would make RL more appealing for real-world applications while also making MPC more flexible and scalable under general learning algorithms. Ultimately, I want to create safe decision-making technologies that “just work” in response to high-level commands.

My PhD is in Applied Mathematics from UBC where I worked with Philip Loewen and Bhushan Gopaluni. Here you can find my thesis on Deep reinforcement learning agents for industrial control system design. The first part of my thesis focuses on the practical implementation of RL and meta-RL for PID tuning in the context of industrial process control. I later developed a general method for synthesizing stabilizing controllers with any RL algorithm using input-output data.

Publications

Most of my papers are linked to arXiv or a DOI. If you can’t find one, feel free to get in touch. You can also find my articles on my Google Scholar profile.

  1. Journal Papers
    1. Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behavior
      , , , ,
      Automatica. 2024.
      [Link] [arXiv]
    2. Machine learning techniques for industrial sensing and control: A survey and practical perspective
      , , , , , , , , ,
      Control Engineering Practice. 2024.
      [Link] [arXiv]
    3. Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system
      , , , ,
      Applied Energy. 2023.
      [Link] [arXiv]
    4. Meta-reinforcement learning for the tuning of PI controllers: An offline approach
      , , , , ,
      Journal of Process Control. 2022.
      [Link] [arXiv]
    5. Deep reinforcement learning with shallow controllers: An experimental application to PID tuning
      , , , , ,
      Control Engineering Practice. 2022.
      [Link] [arXiv]
    6. Toward self‐driving processes: A deep reinforcement learning approach to control
      , , , ,
      AIChE Journal. 2019.
      [Link] [arXiv]
  2. Conference Proceedings
    1. Deep Hankel matrices with random elements
      , , , ,
      Learning for Dynamics & Control Conference. 2024.
      [Link] [arXiv]
    2. Reinforcement learning with partial parametric model knowledge
      , , , ,
      IFAC World Congress. 2023.
      [Link] [arXiv]
    3. A modular framework for stabilizing deep reinforcement learning control
      , , , ,
      IFAC World Congress. 2023.
      [Link] [arXiv]
    4. Meta-reinforcement learning for adaptive control of second order systems
      , , , , ,
      AdCONIP. 2022.
      [Link] [arXiv]
    5. A meta-reinforcement learning approach to process control
      , , , , ,
      AdCHEM. 2021.
      [Link] [arXiv] | Keynote Paper
    6. Reinforcement learning based design of linear fixed structure controllers
      , , , , ,
      IFAC World Congress. 2020.
      [Link] [arXiv]
    7. Optimal PID and antiwindup control design as a reinforcement learning problem
      , , , , ,
      IFAC World Congress. 2020.
      [Link] [arXiv]
    8. Almost Surely Stable Deep Dynamics
      , , , ,
      NeurIPS. 2020.
      [Link] [arXiv] | NeurIPS Spotlight
    9. Modern machine learning tools for monitoring and control of industrial processes: A survey
      , , , , , , , ,
      IFAC World Congress. 2020.
      [Link] [arXiv]
  3. Theses
    1. Deep reinforcement learning agents for industrial control system design

      The University of British Columbia. 2023.
      [Link]
    2. Convex and nonconvex optimization techniques for the constrained Fermat-Torricelli problem

      Portland State University. 2016.
      [Link]