My thesis

Generalization Through the Lens of Learning Dynamics. (arXiv link)


Learning Dynamics and Generalization in Reinforcement Learning. Clare Lyle, Mark Rowland, Will Dabney, Marta Kwiatkowska, Yarin Gal. ICML 2022, RLDM Spotlight. (arXiv link).

Understanding and Preventing Capacity Loss in Reinforcement Learning Clare Lyle, Mark Rowland, Will Dabney. ICLR 2021 (arXiv link).


Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning. Jannik Kossen, Neil Band, Clare Lyle, Aidan N. Gomez, Tom Rainforth, and Yarin Gal. NeurIPS 2021. (arXiv link).

Revisiting the train loss: an efficient performance estimator for neural architecture search. Binxin Ru*, Clare Lyle*, Lisa Schut, Mark van der Wilk, and Yarin Gal. NeurIPS 2021. (arXiv link).

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions Benjie Wang*, Clare Lyle*, Marta Kwiatkowska. IJCAI 2021. (arXiv link).

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning Angelos Filos, Clare Lyle, Yarin Gal, Sergey Levine, Natasha Jaques, Gregory Farquhar. ICML 2021. (arXiv link).

On The Effect of Auxiliary Tasks on Representation Dynamics Clare Lyle*, Mark Rowland*, Georg Ostrovski, Will Dabney, AISTATS 2021. (arXiv link).


A Bayesian Perspective on Training Speed and Model Selection Clare Lyle, Lisa Schut, Binxin Ru, Yarin Gal, Mark van der Wilk, NeurIPS 2020. (arXiv link).

Invariant Causal Prediction for Block MDPs Amy Zhang*, Clare Lyle*, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup, ICML 2020. (arXiv link).


A Geometric Perspective on Optimal Representations in Reinforcement Learning. Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taiga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, Clare Lyle. NeurIPS 2019. (arXiv link)

A Comparative Analysis of Expected and Distributional Reinforcement Learning. Clare Lyle, Pablo Samuel Castro, Marc G. Bellemare. Proceedings of the Thirty-First AAAI Conference, 2019. (arXiv link)


The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation Miles Brundage, Shahar Avin, Jack Clark, Helen Toner, Peter Eckersley, Ben Garfinkel, Allan Dafoe, Paul Scharre, Thomas Zeitzoff, Bobby Filar, Hyrum Anderson, Heather Roff, Gregory C Allen, Jacob Steinhardt, Carrick Flynn, Seán Ó hÉigeartaigh, Simon Beard, Haydn Belfield, Sebastian Farquhar, Clare Lyle, Rebecca Crootof, Owain Evans, Michael Page, Joanna Bryson, Roman Yampolskiy, Dario Amodei. Technical Report.

Preprints and Workshop Papers

Understanding plasticity in neural networks. Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Avila Pires, Razvan Pascanu, Will Dabney. (arXiv link)


Understanding Self-Predictive Learning for Reinforcement Learning. Yunhao Tang and many others. (arXiv link)

Resolving Causal Confusion in Reinforcement Learning via Robust Exploration . Clare Lyle, Amy Zhang, Minqi Jiang, Joelle Pineau, Yarin Gal. ICLR Self-Supervised RL Workshop 2021. (openreview link)

Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning. Andreas Kirsch, Clare Lyle, Yarin Gal. ICML Uncertainty in Deep Learning Workshop 2020. (arXiv link)

On the Benefits of Invariance in Neural Networks. Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal, Benjamin Bloem-Reddy, NeurIPS Workshop on Machine Learning with Guarantees, 2019. (arXiv link)

GAN Q-learning. Thang Doan, Bogdan Mazoure, Clare Lyle (arXiv link)