Harley Wiltzer

  • PhD Student, McGill University & Mila
  • harley.wiltzer@mail.mcgill.ca
  • harwiltz
  • harwiltz
  • CV (last updated July 2024)

Research

  1. Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning.
    Harley Wiltzer*, Marc G. Bellemare, David Meger, Patrick Shafto, Yash Jhaveri*
    To appear at Neural Information Processing Systems (NeurIPS), 2024
  2. Foundations of Multivariate Distributional Reinforcement Learning.
    Harley Wiltzer, Jesse Farebrother, Arthur Gretton, Mark Rowland
    To appear at Neural Information Processing Systems (NeurIPS), 2024
  3. Simplifying Constraint Inference with Inverse Reinforcement Learning.
    Adriana Hugessen, Harley Wiltzer, Glen Berseth
    To appear at Neural Information Processing Systems (NeurIPS), 2024
  4. A Distributional Analogue to the Successor Representation.
    Harley Wiltzer*, Jesse Farebrother*, Arthur Gretton, Yunhao Tang, Andre Barreto, Will Dabney, Marc G. Bellemare, Mark Rowland
    International Conference on Machine Learning (ICML), 2024 Spotlight (top 3.5%)
  5. Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control.
    Nate Rahn*, Pierluca D'Oro*, Harley Wiltzer, Pierre-Luc Bacon, Marc G. Bellemare
    Neural Information Processing Systems (NeurIPS), 2023
  6. Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning.
    Harley Wiltzer, David Meger, Marc G. Bellemare
    International Conference on Machine Learning (ICML), 2022
  7. On the Evolution of Return Distributions in Continuous-Time Reinforcement Learning.
    M.Sc. Thesis.

Author: Harley Wiltzer

Created: 2024-10-17 Thu 14:28

Validate