“Learning Real-World Robot Policies by Dreaming”, 2018-05-20 (; similar):
Learning to control robots directly based on images is a primary challenge in robotics.
However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take time. In this paper, we focus on learning a realistic world model capturing the dynamics of scene changes conditioned on robot actions. Our dreaming model can emulate samples equivalent to a sequence of images from the actual environment, technically by learning an action-conditioned future representation/scene regressor.
This allows the agent to learn action policies (ie. visuomotor policies) by interacting with the dreaming model rather than the real-world. We experimentally confirm that our dreaming model enables robot learning of policies that transfer to the real-world.