An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning

1 code implementation • 2 Aug 2021 • Marco Ewerton, Angel Martínez-González, Jean-Marc Odobez

In this paper, we propose to frame the learning of pushing policies (where to push and how) by DQNs as an image-to-image translation problem and exploit an Hourglass-based architecture.

Image-to-Image Translation Translation