There has been rapid progress in the field of deep reinforcement learning, leading to solutions to difficult control problems such as: playing video games from raw-pixels, controlling high-dimensional motor systems, and mastering the games of Go, Chess and Poker. Nevertheless, animal and human brains are still capable of behaviours that outstrip our best artificial agents, particularly in those capacities that require memory of past events, long-term credit assignment, and exploration in environments where reward is sparse. I will describe agents that use high capacity memories, and new algorithms that leverage these memory stores, to mitigate these limitations. Several of these new models are inspired by the continued interplay between machine learning and neuroscience, and may offer new tools for understanding brain function.

Timothy Lillicrap received an Hon. B.Sc. in Cognitive Science & Artificial Intelligence from the University of Toronto and a Ph.D. in Systems Neuroscience from Queen's University in Canada. He moved to the University of Oxford in 2012 where he worked as a Postdoctoral Research Fellow. In 2014 he joined Google DeepMind as a Research Scientist and became a Senior Research Scientist in 2015. His research focuses on machine learning for optimal control and decision making, as well as using these mathematical frameworks to understand how the brain learns. He has developed new algorithms for exploiting deep neural networks in the context of reinforcement learning, and new recurrent memory architectures for one-shot learning problems. His recent projects have included applications of deep learning to robotics and solving games such as Go.