6 papers
On the geometry and topology of representations: the manifolds of modular addition
Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer +4
The Clock and Pizza interpretations, associated with architectures differing in either uniform or learnable attention, were introduced to argue that different architectural designs…
KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
Eric Zimmermann, Harley Wiltzer, Justin Szeto +2
Recent breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward isotropic Gaussian prio…
Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
Yash Jhaveri, Harley Wiltzer, Patrick Shafto +2
In the pursuit of finding an optimal policy, reinforcement learning (RL) methods generally ignore the properties of learned policies apart from their expected return. Thus, even wh…
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
Arnav Kumar Jain, Harley Wiltzer, Jesse Farebrother +3
In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Traditionally, IRL is treated as an adversaria…
Tractable Representations for Convergent Approximation of Distributional HJB Equations
Julie Alhosh, Harley Wiltzer, David Meger
In reinforcement learning (RL), the long-term behavior of decision-making policies is evaluated based on their average returns. Distributional RL has emerged, presenting techniques…
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
Harley Wiltzer, Marc G. Bellemare, David Meger +2
When decisions are made at high frequency, traditional reinforcement learning (RL) methods struggle to accurately estimate action values. In turn, their performance is inconsistent…