Picture for Andrew Jacobsen

Andrew Jacobsen

An Equivalence Between Static and Dynamic Regret Minimization

Add code
Jun 03, 2024
Viaarxiv icon

Online Linear Regression in Dynamic Environments via Discounting

Add code
May 29, 2024
Viaarxiv icon

Unconstrained Online Learning with Unbounded Losses

Add code
Jun 08, 2023
Viaarxiv icon

Parameter-free Mirror Descent

Add code
Apr 02, 2022
Viaarxiv icon

Continual Auxiliary Task Learning

Add code
Feb 22, 2022
Figure 1 for Continual Auxiliary Task Learning
Figure 2 for Continual Auxiliary Task Learning
Figure 3 for Continual Auxiliary Task Learning
Figure 4 for Continual Auxiliary Task Learning
Viaarxiv icon

Parameter-free Gradient Temporal Difference Learning

Add code
May 10, 2021
Figure 1 for Parameter-free Gradient Temporal Difference Learning
Figure 2 for Parameter-free Gradient Temporal Difference Learning
Figure 3 for Parameter-free Gradient Temporal Difference Learning
Figure 4 for Parameter-free Gradient Temporal Difference Learning
Viaarxiv icon

Meta-descent for Online, Continual Prediction

Add code
Jul 17, 2019
Figure 1 for Meta-descent for Online, Continual Prediction
Figure 2 for Meta-descent for Online, Continual Prediction
Figure 3 for Meta-descent for Online, Continual Prediction
Figure 4 for Meta-descent for Online, Continual Prediction
Viaarxiv icon