Sotabase

Career

· Research Scientist, DeepMind2024–
· PhD Student, University of Oxford Department of Computer Science2022–
· Researcher (developed understanding of distributional reinforcement learning), Google Brain
· Graduate Student, University College, Oxford

Publications (41)

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
arXiv.org · 2018
837
cited
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Neural Information Processing Systems · 2021
160
cited
Invariant Causal Prediction for Block MDPs
International Conference on Machine Learning · 2020
151
cited
Understanding plasticity in neural networks
International Conference on Machine Learning · 2023
138
cited
Understanding and Preventing Capacity Loss in Reinforcement Learning
International Conference on Learning Representations · 2022
136
cited
On the Benefits of Invariance in Neural Networks
arXiv.org · 2020
100
cited
A Geometric Perspective on Optimal Representations for Reinforcement Learning
Neural Information Processing Systems · 2019
94
cited
A Comparative Analysis of Expected and Distributional Reinforcement Learning
AAAI Conference on Artificial Intelligence · 2019
86
cited
On The Effect of Auxiliary Tasks on Representation Dynamics
International Conference on Artificial Intelligence and Statistics · 2021
76
cited
Mixtures of Experts Unlock Parameter Scaling for Deep RL
International Conference on Machine Learning · 2024
64
cited
Deep Reinforcement Learning with Plasticity Injection
Neural Information Processing Systems · 2023
63
cited
Vision-Language Models as a Source of Rewards
arXiv.org · 2023
52
cited
Understanding Self-Predictive Learning for Reinforcement Learning
International Conference on Machine Learning · 2022
43
cited
Speedy Performance Estimation for Neural Architecture Search
Neural Information Processing Systems · 2020
41
cited
Learning Dynamics and Generalization in Deep Reinforcement Learning
International Conference on Machine Learning · 2022
37
cited
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
International Conference on Machine Learning · 2021
27
cited
A Bayesian Perspective on Training Speed and Model Selection
Neural Information Processing Systems · 2020
25
cited
GAN Q-learning
arXiv.org · 2018
19
cited
Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning
arXiv.org · 2020
17
cited
DiscoBAX: Discovery of optimal intervention sets in genomic experiment design
International Conference on Machine Learning · 2023
16
cited
Sotabase
Clare Lyle | Researcher Profile | Sotabase | Sotabase