Błażej Osiński is a researcher at deepsense.ai working on reinforcement learning. His professional experience includes working at Google, Google Brain, Microsoft and Facebook. He was also the first software engineer at Berlin-based startup Segment of 1. Błażej holds a Masters Degree in Computer Science and Bachelors in Mathematics, both from the University of Warsaw.
Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction - substantially more, in fact, than a human would need to learn the same games. How can people learn so quickly? Part of the answer may be that people can learn how the game works and predict which actions will lead to desirable outcomes.
In this webinar we will explore: - How video prediction models can be used to improve the sample efficiency of reinforcement learning? - How to create a model capable of predicting future in Atari games? - How to train the RL agent within “dreams” of another neural network?