Clare Lyle

发表

A Comparative Analysis of Expected and Distributional Reinforcement Learning

Marc G. Bellemare, Clare Lyle, Pablo Samuel Castro, 2019, AAAI.

Invariant Causal Prediction for Block MDPs pdf

Joelle Pineau, Doina Precup, Yarin Gal, 2020, ICML.

Understanding and Preventing Capacity Loss in Reinforcement Learning

Mark Rowland, Will Dabney, Clare Lyle, 2022, ArXiv.

DARTS without a Validation Set: Optimizing the Marginal Likelihood pdf

Yarin Gal, Clare Lyle, Binxin Ru, 2021, ArXiv.

Learning Dynamics and Generalization in Reinforcement Learning

Mark Rowland, Will Dabney, Clare Lyle, 2022, ArXiv.

Understanding and Preventing Capacity Loss in Reinforcement Learning

Mark Rowland, Will Dabney, Clare Lyle, 2022, ICLR.

Learning Dynamics and Generalization in Deep Reinforcement Learning

Mark Rowland, Will Dabney, Clare Lyle, 2022, ICML.

Understanding Self-Predictive Learning for Reinforcement Learning

Charline Le Lan, Pierre H. Richemond, R. Munos, 2022, ICML.

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation pdf

Hyrum S. Anderson, Joanna Bryson, Roman Yampolskiy, 2018, ArXiv.

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions

Clare Lyle, Marta Kwiatkowska, Benjie Wang, 2021, IJCAI.

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Aidan N. Gomez, Clare Lyle, Y. Gal, 2021, NeurIPS.

On the Benefits of Invariance in Neural Networks pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, ArXiv.

Invariant Causal Prediction for Block MDPs

Doina Precup, Clare Lyle, Joelle Pineau, 2020, ICML.

Understanding plasticity in neural networks

Will Dabney, Clare Lyle, Razvan Pascanu, 2023, ArXiv.

Understanding plasticity in neural networks

Will Dabney, Clare Lyle, Razvan Pascanu, 2023, arXiv.org.

Speedy Performance Estimation for Neural Architecture Search

Mark van der Wilk, Clare Lyle, Y. Gal, 2020, NeurIPS.

A Bayesian Perspective on Training Speed and Model Selection pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, NeurIPS.

Deep Reinforcement Learning with Plasticity Injection

Junhyuk Oh, Georg Ostrovski, Will Dabney, 2023, ArXiv.

On The Effect of Auxiliary Tasks on Representation Dynamics

Clare Lyle, Georg Ostrovski, Mark Rowland, 2021, AISTATS.

GAN Q-learning pdf

Clare Lyle, Thang Doan, Bogdan Mazoure, 2018, ArXiv.

Robustness to Pruning Predicts Generalization in Deep Neural Networks pdf

Yarin Gal, Clare Lyle, Aidan N. Gomez, 2021, ArXiv.

A Geometric Perspective on Optimal Representations for Reinforcement Learning

Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, 2019, NeurIPS.

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

S. Levine, Clare Lyle, Angelos Filos, 2021, ICML.

Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning pdf

Yarin Gal, Andreas Kirsch, Clare Lyle, 2020, ArXiv.

The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation

Marc G. Bellemare, R. Munos, Mark Rowland, 2023, ICML.

Quantile Credit Assignment

Georg Ostrovski, R. Munos, Mark Rowland, 2023, International Conference on Machine Learning.

Understanding plasticity in neural networks

Will Dabney, Clare Lyle, Razvan Pascanu, 2023, ICML.

DiscoBAX: Discovery of optimal intervention sets in genomic experiment design

Clare Lyle, Y. Gal, Stefan Bauer, 2023, ICML.

Deep Reinforcement Learning with Plasticity Injection

Junhyuk Oh, Georg Ostrovski, Will Dabney, 2023, ArXiv.

Appendix of Speedy Performance Estimation for Neural Architecture Search

Mark van der Wilk, Clare Lyle, Y. Gal, 2021 .

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, ArXiv.