PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations

RSS 2017 - New Frontiers for Deep Learning in Robotics Workshop

We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state from finite differences in position. In contrast to autoencoders, position-velocity encoders are not trained by image reconstruction, but by making the position-velocity representation consistent with priors about interacting with the physical world. We applied PVEs to several simulated control tasks from pixels and achieved promising preliminary results.

View Publication

Latest research news

View the blog