CL
Clare Lyle
cs.LGcs.AIstat.MLComputer sciencecs.CGcs.CRcs.CYcs.DMcs.NEcs.RO
On Valency
published · living versionsW_y3274kcu·v1 · currentpublished
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
with Miles Brundage, Shahar Avin, Jack Clark, Helen Toner +21
1 version
Preprints & journals
41 papers in the corpus · 2016–2026V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control2608.07870v1 · Donghu Kim, Youngdo Lee, Hojoon Lee et al.2026 · 0 citationsarXiv
Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments2603.06009v2 · Michael Beukman, Khimya Khetarpal, Zeyu Zheng et al.2026 · 0 citationsarXiv
Position: agentic AI orchestration should be Bayes-consistent2605.00742v2 · Theodore Papamarkou, Pierre Alquier, Matthias Bauer et al.2026 · 0 citationsarXiv
Fine-Tuned In-Context Learners for Efficient Adaptation2512.19879v1 · Jorg Bornschein, Clare Lyle, Yazhe Li et al.2025 · 0 citationsarXiv
Plasticity as the Mirror of Empowerment2505.10361v2 · David Abel, Michael Bowling, Andr'e Barreto et al.2025 · 0 citationsarXiv
Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning2507.14736v1 · Rafa\l Surdej, Micha\l Bortkiewicz, Alex Lewandowski et al.2025 · 0 citationsarXiv
Optimizers Qualitatively Alter Solutions And We Should Leverage This2507.12224v1 · Razvan Pascanu, Clare Lyle, Ionut-Vlad Modoranu et al.2025 · 0 citationsarXiv
Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning2407.06756v2 · Augustine N. Mavor-Parker, Matthew J. Sargent, Caswell Barry et al.2024 · 0 citationsarXiv
Agency Is Frame-Dependent2502.04403v1 · David Abel, Andr'e Barreto, Michael Bowling et al.2025 · 0 citationsarXiv
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation1802.07228v2 · Miles Brundage, Shahar Avin, Jack Clark et al.2018 · 495 citationsarXivon Valency
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset2411.04034v1 · Alexandre Galashov, Michalis K. Titsias, Andr'as Gyorgy et al.2024 · 1 citationNeurIPS 2024
Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model2402.07598v2 · Mark Rowland, Li Kevin Wenliang, R'emi Munos et al.2024 · 0 citationsarXiv
Switching between tasks can cause AI to lose the ability to learn.39169242 · Lyle, Clare, Pascanu, Razvan2024 · 2 citationsNature. 2024;632(8026):745-747
Vision-Language Models as a Source of Rewards2312.09187v3 · Kate Baumli, Satinder Baveja, Feryal Behbahani et al.2023 · 3 citationsarXiv
Some Counterexamples for Compatible Triangulations1612.04861v1 · Cody Barnson, Dawn Chandler, Qiao Chen et al.2016 · 0 citationsarXiv
Weight Clipping for Deep Continual and Reinforcement Learning2407.01704v1 · Mohamed Elsayed, Qingfeng Lan, Clare Lyle et al.2024 · 1 citationarXiv
Normalization and effective learning rates in reinforcement learning2407.01800v1 · Clare Lyle, Zeyu Zheng, Khimya Khetarpal et al.2024 · 3 citationsarXiv
Mixtures of Experts Unlock Parameter Scaling for Deep RL2402.08609v3 · Johan Obando-Ceron, Ghada Sokar, Timon Willi et al.2024 · 3 citationsarXiv
A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning2406.02035v1 · Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Avila Pires et al.2024 · 0 citationsarXiv
DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design2312.04064v1 · Clare Lyle, Arash Mehrjou, Pascal Notin et al.2023 · 3 citationsInternational Conference on Machine Learning, 2023
Understanding plasticity in neural networks2303.01486v4 · Clare Lyle, Zeyu Zheng, Evgenii Nikishin et al.2023 · 7 citationsarXiv
Deep Reinforcement Learning with Plasticity Injection2305.15555v2 · Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski et al.2023 · 3 citationsarXiv
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation2305.18388v1 · Mark Rowland, Yunhao Tang, Clare Lyle et al.2023 · 0 citationsarXiv
Generalization Through the Lens of Learning Dynamics2212.05377v1 · Clare Lyle2022 · 0 citationsarXiv
Understanding Self-Predictive Learning for Reinforcement Learning2212.03319v1 · Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond et al.2022 · 1 citationarXiv
Learning Dynamics and Generalization in Reinforcement Learning2206.02126v1 · Clare Lyle, Mark Rowland, Will Dabney et al.2022 · 1 citationarXiv
Understanding and Preventing Capacity Loss in Reinforcement Learning2204.09560v2 · Clare Lyle, Mark Rowland, Will Dabney2022 · 10 citationsarXiv
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning2106.02584v2 · Jannik Kossen, Neil Band, Clare Lyle et al.2021 · 44 citationsarXiv
DARTS without a Validation Set: Optimizing the Marginal Likelihood2112.13023v1 · Miroslav Fil, Binxin Ru, Clare Lyle et al.2021 · 0 citationsarXiv
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning2102.12560v2 · Angelos Filos, Clare Lyle, Yarin Gal et al.2021 · 5 citationsarXiv
Speedy Performance Estimation for Neural Architecture Search2006.04492v2 · Binxin Ru, Clare Lyle, Lisa Schut et al.2020 · 14 citationsarXiv
Provable Guarantees on the Robustness of Decision Rules to Causal Interventions2105.09108v1 · Benjie Wang, Clare Lyle, Marta Kwiatkowska2021 · 1 citationarXiv
Robustness to Pruning Predicts Generalization in Deep Neural Networks2103.06002v1 · Lorenz Kuhn, Clare Lyle, Aidan N. Gomez et al.2021 · 9 citationsarXiv
On The Effect of Auxiliary Tasks on Representation Dynamics2102.13089v1 · Clare Lyle, Mark Rowland, Georg Ostrovski et al.2021 · 2 citationsarXiv
Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning2003.12537v3 · Andreas Kirsch, Clare Lyle, Yarin Gal2020 · 9 citationsarXiv
A Bayesian Perspective on Training Speed and Model Selection2010.14499v1 · Clare Lyle, Lisa Schut, Binxin Ru et al.2020 · 12 citationsarXiv
Invariant Causal Prediction for Block MDPs2003.06016v2 · Amy Zhang, Clare Lyle, Shagun Sodhani et al.2020 · 47 citationsarXiv
On the Benefits of Invariance in Neural Networks2005.00178v1 · Clare Lyle, Mark van der Wilk, Marta Kwiatkowska et al.2020 · 16 citationsarXiv
A Geometric Perspective on Optimal Representations for Reinforcement Learning1901.11530v2 · Marc G. Bellemare, Will Dabney, Robert Dadashi et al.2019 · 52 citationsarXiv
A Comparative Analysis of Expected and Distributional Reinforcement Learning1901.11084v2 · Clare Lyle, Pablo Samuel Castro, Marc G. Bellemare2019 · 55 citationsarXiv
GAN Q-learning1805.04874v3 · Thang Doan, Bogdan Mazoure, Clare Lyle2018 · 9 citationsarXiv
Career total: 54 works. 41 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.