2 papers
cs.LG2024
Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning
Alihan Hüyük, Arndt Ryo Koblitz, Atefeh Mohajeri +1
In image-based reinforcement learning (RL), policies usually operate in two steps: first extracting lower-dimensional features from raw images (the "recognition" step), and then ta…
physics.flu-dyn2018
Direct numerical simulation of particle sedimentation in a Bingham fluid
A. R. Koblitz, S. Lovett, N. Nikiforakis
The settling efficiency, and stability with respect to settling, of a dilute suspension of infinite circular cylinders in a quiescent viscoplastic fluid is examined by means of dir…