Ryan Faulkner

Hi! I'm a Computer Scientist and Machine Learning researcher with a background in reinforcement learning and foundation models. I have worked as a Research Engineer over the past decade at Google Deepmind and I am also a PhD Student at the University of Toronto advised by Zhijing Jin. At GDM I work in the Concordia group led by Joel Leibo.

At a high level my current research focus is on multi-agent systems, LLMs, and social learning. In this context I am interested in memory mechanisms, agent theory of mind, collective decision making, and simulating political systems.

News

Publications

fig
Sima 2: A Generalist Embodied Agent for Virtual Worlds Sima Team. Google Deepmind arXiv preprint, 2025. Showcase
fig
Scaling Instructable Agents Across Many Simulated Worlds Sima Team. Google Deepmind arXiv preprint, 2024
fig
Solving Reasoning Tasks with a Slot Transformer R. Faulkner, D. Zoran arXiv preprint, 2022
fig
Rapid Task-Solving in Novel Environments *S. Ritter, *R. Faulkner, L. Sartran, A. Santoro, M. Botvinick, D. Raposo In International Conference on Learning Representations, 2021.
fig
OpenSpiel: A Framework for Reinforcement Learning in Games M. Lanctot, E. Lockhart, J.B. Lespiau, V. Zambaldi, S. Upadhyay, J. Pérolat, S. Srinivasan, F. Timbers, K. Tuyls, S. Omidshafiei, D. Hennes, D. Morrill, P. Muller, T. Ewalds, R. Faulkner, J. Kramár, B. De Vylder, B. Saeta, J. Bradbury, D. Ding, S. Borgeaud, M. Lai, J. Schrittwieser, T. Anthony, E. Hughes, I. Danihelka, J. Ryan-Davis arXiv preprint, 2019
fig
Generalization of Reinforcement Learners with Working and Episodic Memory *M. Fortunato, *M. Tan, *R. Faulkner, *S. Hansen, A. Puigdomènech Badia, et al. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
fig
Interval Timing in Deep Reinforcement Learning Agents B. Deverett, R. Faulkner, M. Fortunato, G. Wayne, J.Z. Leibo 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
fig
Relational Inductive Biases, Deep Learning, and Graph Networks P.W. Battaglia, J.B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner, et al. arXiv preprint, 2018
fig
Relational Recurrent Neural Networks *A. Santoro, *R. Faulkner, D. Raposo, J. Rae, M. Chrzanowski, et al. 32rd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada.
fig
Grounded Language Learning in a Simulated 3D World K.M. Hermann, F. Hill, F. Wang, S. Green, R. Faulkner, et al. arXiv preprint, 2017
fig
Etiquette in wikipedia: Weaning new editors... R. Faulkner, S. Walling, M. Pinchuk WikiSym 2012, Linz, Austria
fig
Dyna Learning with Deep Belief Networks R. Faulkner McGill University (M.Sc. Thesis), 2010
fig
Dyna Planning Using a Feature Based Generative Model R. Faulkner, D. Precup 24th Conference on Neural Information Processing Systems (NIPS 2010), Vancouver, Canada.

* denotes equal contribution