Murray Shanahan, Imperial College London Deep Learning Summit, London, 2016, rework DL

View more videos from the 2016 Deep Learning Summit in London here: Enhancing Deep Reinforcement Learning with Symbolic Reasoning Despite its dramatic successes, contemporary deep reinforcement learning methods have certain shortcomings. Because they rely on the statistics of large datasets, they tend to learn very slowly. We see this, for example, in DeepMind s DQN, which attains superhuman performance after playing a very large number of (certain) Atari games, but takes