activity
20152021
most citedMT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

35 citations · 140 across the 13 of their papers we have counts for

collaborators
Showing 2017Show all

1 paper · 1 filter

cs.RO2017★ 35 cited

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

Rico Jonschkowski, Roland Hafner, Jonathan Scholz +1

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 i…