Комментарии:
İmpressive, very nice work
ОтветитьI think we need ant robots, the can carry hundreds times they weight...
ОтветитьThis gave me anxiety
ОтветитьIf I don't have to pick up their 💩💩 or exercise them, I'll take one!
Ответитьwhat are the sensor to learn to walk? lidar? camera?
ОтветитьI am confused.
We already saw your quadropods like ANYmal being tested under real world conditions.
What is so different now, that you are back to virtual and climbing over cardboard boxes?
Why robots has legs? There is not more effective to use wheels?
ОтветитьWhat environment you use for simulation ?
ОтветитьUsing massive clone jutsu learn things faster copied from baritone😂
Ответитьboston dynamics be like "we just wasted 30 years of our lives"
ОтветитьWhat parameters make a robot in the iteration successful? Distance travelled?
ОтветитьIncredible Work!
ОтветитьMassive Parallel Deep RL aka Random Search
ОтветитьI get anxiety when I think about how a proper contact simulation for a single robot struggles to run in real time on my computer..
Ответитьawesome! now do it with interacting robots (batching will no longer work?) :)
ОтветитьGeez, how many cpu cores does it take to run this many instances in parallel?
Ответитьgreat
Ответить