[altvali]

I've participated in the NIPS "Learning to run" competition last year. It only computes motion in one direction (forward-backward, the model can't go left or right). What turned me off was the fact that object collision was handled poorly. You can't see a model that actually makes effort to avoid obstacles, instead all top solutions go through objects.

[kidzik]

That's only one-side of the story. It is actually a very accurate contact model. The problem is that it's also computationally expensive and therefore we reduce the stiffness of objects to make it faster. It's basically a trade-off between the accuracy and speed. In gaming engines you have speed and it looks good, but then it's impossible to generalize for real-life applications (because the contact is inaccurate).

[electricslpnsld]

> The problem is that it's also computationally expensive and therefore we reduce the stiffness of objects to make it faster.

Are y'all using penalty methods for the collisions? Which model does it use?

[roel_v]

So all 'joints' only move in 2d, am I getting that right?

[kidzik]

In the 2017 challenge yes. This year we are using a 3d model.