Re: Abominations, schedule & Euler angles

I very much agree with Mike Jost (and others) in that changes to the physics
should not be used as a means to penalize annoying controllers; such changes
should only be motivated by enhanced realism.
I believe two lessons can be learned fom the last contest, 1) a sucessful
controller must be robust as well as sophisticated, and 2) the evolution of
the controllers will accelerate towards the end of the contest. Curry and
Sonovabic will force sophisticated controllers to be more robust, and this
is a good thing! In the end however, I think they will be beaten (if they do
not evolve).


A Question: Is the physical proporties of the surrounding grounds identical
to those of the tatami? When using learning algorithms it seems much simpler
to let the robot walk on the ground.

Best,
Anders Lyhagen


To unsubscribe from this group, send an email to:
[email protected]

 

Yahoo! Groups Links

To visit your group on the web, go to:
 http://groups.yahoo.com/group/webots-contest/

To unsubscribe from this group, send an email to:
 [email protected]

Your use of Yahoo! Groups is subject to:
 http://docs.yahoo.com/info/terms/