Скачать с ютуб Matt Botvinick-Deep reinforcement learning and its neuroscientific implications в хорошем качестве

Matt Botvinick-Deep reinforcement learning and its neuroscientific implications

ViDA 2021 - Tuesday June 22nd 2021 Matt Botvinick Director of Neuroscience and Team Lead in AGI Research, DeepMind ; Honorary Professor, Gatsby Computational Neuroscience Unit, University College London Deep reinforcement learning and its neuroscientific implications The last few years have seen some dramatic developments in artificial intelligence research. What implications might these have for neuroscience? Investigations of this question have, to date, focused largely on deep neural networks trained using supervised learning, in tasks such as image classification. In this talk, I'll discuss another area of recent AI work which has so far received less attention from neuroscientists, but which may have more profound implications: Deep reinforcement learning. Deep RL provides a rich framework for studying the interplay among learning, representation and decision-making, offering to the brain sciences a new set of research tools and a wide range of novel hypotheses. I'll provide a high level introduction to deep RL and survey some of its key implications for research on the brain and behavior, with a particular focus on potential implications for understanding dopaminergic function.