CB
Charles Blundell
cs.LGstat.MLcs.AIcs.CVcs.DScs.CLcs.NEcs.SIneurosciencephysics.comp-ph
On Valency
published · living versionsW_45caf8hg·v1 · currentpublished
Model-Free Episodic Control
with Benigno Uria, Alexander Pritzel, Yazhe Li, Avraham Ruderman +4
1 version
W_dq4s63wz·v1published
W_849y4y56·v1published
Preprints & journals
60 papers in the corpus · 2010–2024The CLRS-Text Algorithmic Reasoning Language Benchmark2406.04229v1 · Larisa Markeeva, Sean McLeish, Borja Ibarz et al.2024 · 0 citationsarXiv
Synth: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings2403.07750v2 · Sahand Sharifzadeh, Christos Kaplanis, Shreya Pathak et al.2024 · 3 citationsarXiv
Improving fine-grained understanding in image-text pre-training2401.09865v1 · Ioana Bica, Anastasija Ili'c, Matthias Bauer et al.2024 · 4 citationsarXiv
Unlocking the Power of Representations in Long-term Novelty-based Exploration2305.01521v1 · Alaa Saade, Steven Kapturowski, Daniele Calandriello et al.2023 · 0 citationsarXiv
Neural Algorithmic Reasoning with Causal Regularisation2302.10258v2 · Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz et al.2023 · 3 citationsarXiv
SemPPL: Predicting pseudo-labels for better contrastive representations2301.05158v2 · Matko Bosnjak, Pierre H. Richemond, Nenad Tomasev et al.2023 · 4 citationsarXiv
A Generalist Neural Algorithmic Learner2209.11142v2 · Borja Ibarz, Vitaly Kurin, George Papamakarios et al.2022 · 12 citationsarXiv
Human-level Atari 200x faster2209.07550v1 · Steven Kapturowski, V'ictor Campos, Ray Jiang et al.2022 · 4 citationsarXiv
The CLRS Algorithmic Reasoning Benchmark2205.15659v2 · Petar Velickovi'c, Adria Puigdomenech Badia, David Budden et al.2022 · 9 citationsarXiv
Retrieval-Augmented Reinforcement Learning2202.08417v4 · Anirudh Goyal, Abram L. Friesen, Andrea Banino et al.2022 · 23 citationsarXiv
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?2201.05119v2 · Nenad Tomasev, Ioana Bica, Brian McWilliams et al.2022 · 22 citationsarXiv
Advancing mathematics by guiding human intuition with AI.34853458 · Davies, Alex, Veličković, Petar, Buesing, Lars et al.2022 · 452 citationsNature. 2021;600(7887):70-74
Towards combinatorial invariance for Kazhdan-Lusztig polynomials2111.15161v1 · Charles Blundell, Lars Buesing, Alex Davies et al.2021 · 17 citationsRepresent. Theory 26 (2022), 1145-1191
Normalizing flows for atomic solids2111.08696v2 · Peter Wirnsberger, George Papamakarios, Borja Ibarz et al.2021 · 42 citationsarXiv
Reasoning-Modulated Representations2107.08881v2 · Petar Velickovi'c, Matko Bosnjak, Thomas Kipf et al.2021 · 1 citationarXiv
PonderNet: Learning to Ponder2107.05407v2 · Andrea Banino, Jan Balaguer, Charles Blundell2021 · 24 citationsarXiv
CoBERL: Contrastive BERT for Reinforcement Learning2107.05431v2 · Andrea Banino, Adria Puidomenech Badia, Jacob Walker et al.2021 · 20 citationsarXiv
Neural algorithmic reasoning.34286298 · Veličković, Petar, Blundell, Charles2021 · 39 citationsPatterns (New York, N.Y.). 2021;2(7):100273
Emphatic Algorithms for Deep Reinforcement Learning2106.11779v1 · Ray Jiang, Tom Zahavy, Zhongwen Xu et al.2021 · 7 citationsProceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021
Neural Production Systems: Learning Rule-Governed Visual Dynamics2103.01937v3 · Anirudh Goyal, Aniket Didolkar, Nan Rosemary Ke et al.2021 · 0 citationsarXiv
Persistent Message Passing2103.01043v2 · Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell et al.2021 · 4 citationsarXiv
Coordination Among Neural Modules Through a Shared Global Workspace2103.01197v2 · Anirudh Goyal, Aniket Didolkar, Alex Lamb et al.2021 · 59 citationsarXiv
Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning2102.13515v3 · V'ictor Campos, Pablo Sprechmann, Steven Hansen et al.2021 · 13 citationsarXiv
A model of egocentric to allocentric understanding in mammalian brains10.1101/2020.11.11.378141v2 · Uria, B., Ibarz, B., Banino, A. et al.2020 · 48 citationsbioRxiv
Representation Learning via Invariant Causal Mechanisms2010.07922v1 · Jovana Mitrovic, Brian McWilliams, Jacob Walker et al.2020 · 106 citationsarXiv
Targeted free energy estimation via learned mappings.33086827 · Wirnsberger, Peter, Ballard, Andrew J, Papamakarios, George et al.2020 · 96 citationsThe Journal of chemical physics. 2020;153(14):144112
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems2006.16225v5 · Anirudh Goyal, Alex Lamb, Phanideep Gampa et al.2020 · 15 citationsarXiv
Pointer Graph Networks2006.06380v2 · Petar Velickovi'c, Lars Buesing, Matthew C. Overlan et al.2020 · 18 citationsarXiv
Agent57: Outperforming the Atari Human Benchmark2003.13350v1 · Adria Puigdomenech Badia, Bilal Piot, Steven Kapturowski et al.2020 · 215 citationsarXiv
Never Give Up: Learning Directed Exploration Strategies2002.06038v1 · Adria Puigdomenech Badia, Pablo Sprechmann, Alex Vitvitskyi et al.2020 · 169 citationsarXiv
MEMO: A Deep Network for Flexible Combination of Episodic Memories2001.10913v1 · Andrea Banino, Adria Puigdomenech Badia, Raphael Koster et al.2020 · 17 citationsarXiv
Shaping representations through communication: community size effect in artificial learning systems1912.06208v1 · Olivier Tieleman, Angeliki Lazaridou, Shibl Mourad et al.2019 · 11 citationsarXiv
Generalization of Reinforcement Learners with Working and Episodic Memory1910.13406v2 · Meire Fortunato, Melissa Tan, Ryan Faulkner et al.2019 · 35 citations33rd Conference on Neural Information Processing Systems (Neurips 2019)
Neural Execution of Graph Algorithms1910.10593v2 · Petar Velickovi'c, Rex Ying, Matilde Padovano et al.2019 · 26 citationsarXiv
Confidence modulates exploration and exploitation in value-based learning.31086679 · Boldt, Annika, Blundell, Charles, De Martino, Benedetto2026 · 121 citationsNeuroscience of consciousness. 2019;2019(1):niz004
Reinforcement Learning, Fast and Slow.31003893 · Botvinick, Matthew, Ritter, Sam, Wang, Jane X et al.2020 · 666 citationsTrends in cognitive sciences. 2019;23(5):408-422
Fast deep reinforcement learning using online adjustments from the past1810.08163v1 · Steven Hansen, Pablo Sprechmann, Alexander Pritzel et al.2018 · 24 citationsarXiv
Been There, Done That: Meta-Learning with Episodic Recall1805.09692v2 · Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson et al.2018 · 60 citationsarXiv
Pushing the bounds of dropout1805.09208v2 · G'abor Melis, Charles Blundell, Tom'as Kocisk'y et al.2018 · 10 citationsarXiv
Vector-based navigation using grid-like representations in artificial agents.29743670 · Banino, Andrea, Barry, Caswell, Uria, Benigno et al.2018 · 683 citationsNature. 2018;557(7705):429-433
Memory-based Parameter Adaptation1802.10542v1 · Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae et al.2018 · 54 citationsarXiv
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning1707.08475v2 · Irina Higgins, Arka Pal, Andrei A. Rusu et al.2017 · 219 citationsarXiv
Noisy Networks for Exploration1706.10295v3 · Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot et al.2017 · 665 citationsarXiv
Bayesian Recurrent Neural Networks1704.02798v4 · Meire Fortunato, Charles Blundell, Oriol Vinyals2017 · 145 citationsarXiv
Neural Episodic Control1703.01988v1 · Alexander Pritzel, Benigno Uria, Sriram Srinivasan et al.2017 · 213 citationsarXiv
Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees1702.08833v1 · Daniel Zoran, Balaji Lakshminarayanan, Charles Blundell2017 · 6 citationsarXiv
PathNet: Evolution Channels Gradient Descent in Super Neural Networks1701.08734v1 · Chrisantha Fernando, Dylan Banarse, Charles Blundell et al.2017 · 619 citationsarXiv
Computations Underlying Social Hierarchy Learning: Distinct Neural Mechanisms for Updating and Representing Self-Relevant Information.27930904 · Kumaran, Dharshan, Banino, Andrea, Blundell, Charles et al.2017 · 156 citationsNeuron. 2016;92(5):1135-1147
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles1612.01474v3 · Balaji Lakshminarayanan, Alexander Pritzel, Charles Blundell2016 · 3,663 citationsarXiv
Learning to reinforcement learn1611.05763v3 · Jane X Wang, Zeb Kurth-Nelson, Dhruva Tirumala et al.2016 · 579 citationsarXiv
Career total: 79 works. 60 are in this corpus.Showing the 50 most recent.
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.