Publications

Filter by type:

Mehdi Mirza, Andrew Jaegle, Jonathan J. Hunt, Arthur Guez, Saran Tunyasuvunakool, Alistair Muldal, Théophane Weber, Peter Karkus, Sébastien Racanière, Lars Buesing, Timothy Lillicrap, Nicolas Heess. Physically Embedded Planning Problems: New Challenges for Reinforcement Learning. Preprint, 2020.

Andre Barreto, Diana Borsa, Shaobo Hou, Gheorghe Comanici, Eser Aygün, Philippe Hamel, Daniel Toyama, JJ Hunt, Shibl Mourad, David Silver, Doina Precup. The Option Keyboard: Combining Skills in Reinforcement Learning. NeurIPS, 2019.

Hunt JJ, Andre Barreto, Timothy P Lillicrap, Nicolas Heess. Composing Entropic Policies using Divergence Correction. ICML, 2019.

Hunt JJ, Andre Barreto, Timothy P Lillicrap, Nicolas Heess. Transfer in Reinforcement Learning with Successor Features and Generalised Policy Improvement. NeurIPS Infer2Control Workshop, 2018.

Barreto A, Dabney W, Munos R, Hunt JJ¹, Schaul T, Silver D, van Hasselt H. Successor Features for Transfer in Reinforcement Learning. NIPS, 2017.

Barreto A, Dabney W, Munos R, Hunt JJ, Schaul T, Silver D, van Hasselt H. Transfer in Reinforcement Learning with Successor Features and Generalised Policy Improvement. ICLR Lifelong Learning Workshop, 2017.

Rae JW¹, Hunt JJ¹, Harley T, Danihelka I, Senior A, Wayne G, Graves A, Lillicrap TP. Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes. NIPS, 2016.

Dulca-Arnold G, Evans R, van Hasselt H, Sunehag P, Lillicrap TP, Hunt JJ, Mann, T, Weber T, Degris T, Coppin B. Deep Reinforcement Learning in Large Discrete Action Spaces. Preprint, 2016.

Lillicrap TP¹, Hunt JJ¹, Pritzel A, Heess N, Erez T, Tassa Y, Silver D. Continuous control with deep reinforcement learning. ICLR, 2016.

Heess N¹, Hunt JJ¹, Lillicrap TP, Silver D. Memory-based control with recurrent neural networks. Neural Information Processing Systems Deep Reinforcement Learning Workshop, 2015.

Hughes NJ, Hunt JJ, Cloherty SL, Ibbotson MR, Sengpiel F, Goodhill GJ. Stripe-rearing changes multiple aspects of the structure of primary visual cortex. Vision Research, 2014.

Hunt JJ, Dayan P, Goodhill GJ. Sparse coding can predict primary visual cortex receptive field changes induced by abnormal visual input. PLoS Computational Biology, 2013.

Hunt JJ, Ibbotson MR, Goodhill GJ. Sparse coding on the spot: spontaneous retinal waves suffice for orientation selectivity. Neural Computation, 2012.

Hunt JJ, Mattingley JB, Goodhill GJ. Randomly oriented edge arrangements dominate naturalistic arrangements in binocular rivalry. Vision Research, 2012.

Forbes EM¹, Hunt JJ¹, Goodhill GJ. The combinatorics of neurite self-avoidance.. Neural Computation, 2011.

Hunt JJ, Bosking WH, Goodhill GJ. Statistical structure of lateral connections in the primary visual cortex. Neural Systems & Circuits, 2011.

Hunt JJ. Natural scene statistics and the development of the primary visual cortex. PhD Thesis, 2011.

Hunt JJ¹, Giacomantonio CE¹, Tang H, Mortimer D, Jaffer S, Vorobyov V, Ericksson G, Sengpiel F, Goodhill GJ. Natural scene statistics and the structure of orientation maps in the visual cortex. Neuroimage, 2009.

Hunt JJ. Polysaccharide sequence reconstruction from digest patterns. Undergraduate Honours Thesis, 2006.

Hunt JJ, Cameron RG, Williams MAK. On the simulation of enzymatic digest patterns: the fragmentation of oligomeric and polymeric galacturonides by endo-polygalacturonase II. Biochimica et Biophysica Acta, 2006.

PDF Preprint DOI

Hunt JJ. Molecular Dynamics Simulation of Two Possible Mixing Configurations. Undergraduate Report, 2005.