In this work, we investigate the potential of improving multi-task train...
Pick-and-place is an important manipulation task in domestic or manufact...
The purpose of multi-task reinforcement learning (MTRL) is to train a si...
Deep learning has recently achieved significant progress in trajectory
f...
Motion forecasting in highly interactive scenarios is a challenging prob...
Animals are able to imitate each others' behavior, despite their differe...
Proposing grasp poses for novel objects is an essential component for an...
Generating diverse and comprehensive interacting agents to evaluate the
...