Connectionists: Real-Robot Challenge 2022 -- offline reinforcement learning for real robots

[Georg Martius]

Dear Colleagues,

We are happy to announce the Real-Robot Challenge 2022:

It is time to test offline reinforcement learning methods in the real world!
Take part in our http://real-robot-challenge.com NeurIPS competition.

The task is to use pre-recorded data to learn how to manipulate a cube 
with the TriFinger robot. You will then be able to run the policy on a 
real robot at the Max Planck Institute for Intelligent Systems in a 
remote fashion  (as easy as submitting a compute job).

Please encourage your colleagues to take part and spread the word.
https://twitter.com/robo_challenge/status/1549059071332040709?s=20&t=wDuocEfUp6NtUNBSVTGr8A

Many thanks and regards,
   The RRC-Organizers

[Georg Martiu, Nico Gürtler, Felix Widmaier, Cansu Sancaktar, Sebastian 
Blaes, Pavel Kolev, Stefan Bauer, Manuel Wüthrich, Markus Wulfmeier, 
Martin Riedmiller, Arthur Allshire, Annika Buchholz, Thomas 
Steinbrenner, Vincent Berenz, Bernhard Schölkopf]