7 citations · 10 across the 7 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
Meta-Learning Mini-Batch Risk Functionals
Jacob Tyo, Zachary C. Lipton
Supervised learning typically optimizes the expected value risk functional of the loss, but in many cases, we want to optimize for other risk functionals. In full-batch gradient de…
cs.LG2020★ 3 cited
How Transferable are the Representations Learned by Deep Q Agents?
Jacob Tyo, Zachary Lipton
In this paper, we consider the source of Deep Reinforcement Learning (DRL)'s sample complexity, asking how much derives from the requirement of learning useful representations of e…