Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Alex Kearney

What's a Good Prediction? Issues in Evaluating General Value Functions Through Error

Jan 23, 2020
Alex Kearney, Anna Koop, Patrick M. Pilarski

* Submitted to AAMAS 

  Access Paper or Ask Questions

Women, politics and Twitter: Using machine learning to change the discourse

Nov 25, 2019
Lana Cuthbertson, Alex Kearney, Riley Dawson, Ashia Zawaduk, Eve Cuthbertson, Ann Gordon-Tighe, Kory W Mathewson

* 8 pages, 2 figures. Presented at the NeurIPS Joint Workshop on AI for Social Good at NeurIPS 2019 

  Access Paper or Ask Questions

Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures

Aug 15, 2019
Johannes Günther, Nadia M. Ady, Alex Kearney, Michael R. Dawson, Patrick M. Pilarski

  Access Paper or Ask Questions

When is a Prediction Knowledge?

Apr 18, 2019
Alex Kearney, Patrick M. Pilarski

* Accepted to RLDM 2019 

  Access Paper or Ask Questions

Making Meaning: Semiotics Within Predictive Knowledge Architectures

Apr 18, 2019
Alex Kearney, Oliver Oxton

* Accepted to RLDM 2019 

  Access Paper or Ask Questions

Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning

Mar 08, 2019
Alex Kearney, Vivek Veeriah, Jaden Travnik, Patrick M. Pilarski, Richard S. Sutton

  Access Paper or Ask Questions

TIDBD: Adapting Temporal-difference Step-sizes Through Stochastic Meta-descent

Apr 10, 2018
Alex Kearney, Vivek Veeriah, Jaden B. Travnik, Richard S. Sutton, Patrick M. Pilarski

* Version as submitted to the 31st Conference on Neural Information Processing Systems (NIPS 2017) on May 19, 2017. 9 pages, 5 figures. Extended version in preparation for journal submission 

  Access Paper or Ask Questions