| The malicious use of artificial intelligence: Forecasting, prevention, and mitigation M Brundage, S Avin, J Clark, H Toner, P Eckersley, B Garfinkel, A Dafoe, ... arXiv preprint arXiv:1802.07228, 2018 | 1227 | 2018 |
| Invariant causal prediction for block mdps A Zhang, C Lyle, S Sodhani, A Filos, M Kwiatkowska, J Pineau, Y Gal, ... International Conference on Machine Learning, 11214-11224, 2020 | 153 | 2020 |
| Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning J Kossen, N Band, C Lyle, AN Gomez, T Rainforth, Y Gal NeurIPS 2021, 2021 | 130 | 2021 |
| A geometric perspective on optimal representations for reinforcement learning MG Bellemare, W Dabney, R Dadashi, AA Taiga, PS Castro, NL Roux, ... NeurIPS 2019, 2019 | 107 | 2019 |
| Understanding and preventing capacity loss in reinforcement learning C Lyle, M Rowland, W Dabney arXiv preprint arXiv:2204.09560, 2022 | 105 | 2022 |
| A comparative analysis of expected and distributional reinforcement learning C Lyle, MG Bellemare, PS Castro Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 4504-4511, 2019 | 100 | 2019 |
| On the benefits of invariance in neural networks C Lyle, M van der Wilk, M Kwiatkowska, Y Gal, B Bloem-Reddy arXiv preprint arXiv:2005.00178, 2020 | 97* | 2020 |
| Understanding plasticity in neural networks C Lyle, Z Zheng, E Nikishin, BA Pires, R Pascanu, W Dabney International Conference on Machine Learning, 23190-23211, 2023 | 77 | 2023 |
| On The Effect of Auxiliary Tasks on Representation Dynamics C Lyle, M Rowland, G Ostrovski, W Dabney AISTATS 2021, 2021 | 77 | 2021 |
| A Speedy Performance Estimator for Neural Architecture Search B Ru, C Lyle, L Schut, M van der Wilk, Y Gal NeurIPS 2021, 2020 | 56 | 2020 |
| Deep reinforcement learning with plasticity injection E Nikishin, J Oh, G Ostrovski, C Lyle, R Pascanu, W Dabney, A Barreto Advances in Neural Information Processing Systems 36, 2024 | 35 | 2024 |
| PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning A Filos, C Lyle, Y Gal, S Levine, N Jaques, G Farquhar ICML 2021, 2021 | 35 | 2021 |
| Understanding self-predictive learning for reinforcement learning Y Tang, ZD Guo, PH Richemond, BA Pires, Y Chandak, R Munos, ... International Conference on Machine Learning, 33632-33656, 2023 | 32 | 2023 |
| Learning dynamics and generalization in deep reinforcement learning C Lyle, M Rowland, W Dabney, M Kwiatkowska, Y Gal International Conference on Machine Learning, 14560-14581, 2022 | 29 | 2022 |
| A Bayesian Perspective on Training Speed and Model Selection C Lyle, L Schut, B Ru, Y Gal, M van der Wilk Proceedings of the 33rd International Conference on Neural Information …, 2020 | 29 | 2020 |
| Disentangling the causes of plasticity loss in neural networks C Lyle, Z Zheng, K Khetarpal, H van Hasselt, R Pascanu, J Martens, ... arXiv preprint arXiv:2402.18762, 2024 | 22 | 2024 |
| Gan q-learning T Doan, B Mazoure, C Lyle arXiv preprint arXiv:1805.04874, 2018 | 19 | 2018 |
| Unpacking information bottlenecks: Unifying information-theoretic objectives in deep learning A Kirsch, C Lyle, Y Gal arXiv preprint arXiv:2003.12537, 2020 | 16 | 2020 |
| Vision-language models as a source of rewards K Baumli, S Baveja, F Behbahani, H Chan, G Comanici, S Flennerhag, ... arXiv preprint arXiv:2312.09187, 2023 | 14 | 2023 |
| Robustness to pruning predicts generalization in deep neural networks L Kuhn, C Lyle, AN Gomez, J Rothfuss, Y Gal arXiv preprint arXiv:2103.06002, 2021 | 14 | 2021 |
Yarin GalAssociate Professor, University of OxfordVerified email at cs.ox.ac.uk