Skip navigation
Please use this identifier to cite or link to this item:
Title: PAC-Bayes Regularization for Learning Controllers that Generalize Across Environments
Authors: Goldstein, Maxwell
Advisors: Arora, Sanjeev
Abbe, Emmanuel
Department: Mathematics
Class Year: 2018
Abstract: We bound the error rate of a robotic grasping controller in novel environments by connecting recent work involving PAC-Bayes regularization to algorithmic decision making. Training a controller on the KUKA robot in the Bullet physics simulator, we compute a PAC-Bayes on the learned controller and show generalization bounds on the performance of the controller in new environments.
Type of Material: Princeton University Senior Theses
Language: en
Appears in Collections:Mathematics, 1934-2020

Files in This Item:
File SizeFormat 
GOLDSTEIN-MAXWELL-THESIS.pdf338.85 kBAdobe PDF    Request a copy

Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.