Harley Wiltzer
Research
- 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 - Foundations of Multivariate Distributional Reinforcement Learning.
Harley Wiltzer, Jesse Farebrother, Arthur Gretton, Mark Rowland
To appear at Neural Information Processing Systems (NeurIPS), 2024 - Simplifying Constraint Inference with Inverse Reinforcement Learning.
Adriana Hugessen, Harley Wiltzer, Glen Berseth
To appear at Neural Information Processing Systems (NeurIPS), 2024 - 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%) - 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 - Distributional Hamilton-Jacobi-Bellman Equations for
Continuous-Time Reinforcement Learning.
Harley Wiltzer, David Meger, Marc G. Bellemare
International Conference on Machine Learning (ICML), 2022 - On the Evolution of Return Distributions in Continuous-Time
Reinforcement Learning.
M.Sc. Thesis.