Mark Crowley

Site being updated, see my Research Lab page for current information.

My research seeks dependable and transparent ways to augment human decision making in complex domains in the presence of spatial structure, large scale streaming data, or uncertainty. My focus is on developing new algorithms within the fields of Reinforcement Learning, Deep Learning and Ensemble Methods, and Manifold Learning (Dimensionality Reduction).
I often work in collaboration with researchers in applied fields such as Computational Sustainability (including Sustainable Forest Management), Autonomous Driving, AI for Physics (including Combustion Modelling and Digital Chemistry) and Medical Imaging.

note for potential graduate students

The global interest in AI/ML/RL is infectious and it is truly an exciting time to be in research in this field. However, interested students should be aware that I rarely accept new graduate students except ones that I know through courses I teach or other interactions at UWaterloo, at conferences, or through referrals from other colleagues. Unfortunately, if you email me with your interest in graduate school I probably will not be able to reply as I receive many such emails every day. Good luck in your search.

writing

Besides my publications, you can follow my Computationally Thinking blog or @compthink on twitter for links and thoughts on Artificial Intellgience, Machine Learning and how technology and science are advancing.

news

Oct 14, 2021 Autoline.tv interview about our Driver Behaviour Learning project with Magna International.
more: Autoline.tv interview about our Driver Behaviour Learning project with Magna International.
Sep 28, 2021 Exciting new paper accepted to ACML 2021!
more: Vector Transport Free Riemannian LBFGS for Optimization on Symmetric Positive Definite Matrix Manifolds
Jun 27, 2021 Paper on QQE algorithm accepted by MLWA Journal
more: Quantile--Quantile Embedding for Distribution Transformation and Manifold Embedding

selected showcase publications

  1. Generative locally linear embedding: A module for manifold unfolding and visualization
    Ghojogh, Benyamin, Ghodsi, Ali, Karray, Fakhri, and Crowley, Mark
    Software Impacts 2021
  2. Vector Transport Free Riemannian LBFGS for Optimization on Symmetric Positive Definite Matrix Manifolds
    Godaz, Reza, Ghojogh, Benyamin, Hosseini, Reshad, Monsefi, Reza, Karray, Fakhri, and Crowley, Mark
    In Asian Conference on Machine Learning (ACML) 2021
  3. Partially Observable Mean Field Reinforcement Learning
    Ganapathi Subramanian, Sriram, Taylor, Matthew, Crowley, Mark, and Poupart, Pascal
    In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS) 2021
  4. Active Measure Reinforcement Learning for Observation Cost Minimization: A framework for minimizing measurement costs in reinforcement learning
    Bellinger, Colin, Coles, Rory, Crowley, Mark, and Tamblyn, Isaac
    In Canadian Conference on Artificial Intelligence 2021
  5. Recognition of a Robot’s Affective Expressions under Conditions with Limited Visibility
    Ghafurian, Moojan, Akgun, Sami Alperen, Crowley, Mark, and Dautenhahn, Kerstin
    In 18th International Conference promoted by the IFIP Technical Committee 13 on Human–Computer Interaction (INTERACT 2021) 2021