Wow!! The demonstration where it learned to recover after being knocked over made me so excited! I think its so impressive that it was able to recover! Really neat stuff!
@pangolin414
12 жыл бұрын
I'm with you completely. The printer seems really pleased with itself.
@reid-dye
Жыл бұрын
Wow! It looks like the wobbliness in the frame is being compensated for like learned input shaping! that's awesome.
@k4mpoeng
3 жыл бұрын
0:56 my entire nerves system when my crush smiling at me
@Bibibosh
3 жыл бұрын
Wall-E
@JonathonReinhart
11 жыл бұрын
I think a system with less mechanical backlash would have performed better and learned more quickly.
@sayantandasgupta9605
7 жыл бұрын
A little addition of LQR control will keep the pendulum on top.
@ww54ww
13 жыл бұрын
Amazing! made me laugh from excitement :D
@TrancorWD
14 жыл бұрын
Very impressive. I've been trying to set up stuff like this (AI), but in a real time 3d environment, so physics are a little less real but this is really nice.
@ShadowRobot
14 жыл бұрын
Excellent, would love to see it do this on a mobile platform.
@okboing
3 жыл бұрын
That machine sounds like it's breaking itself apart
@peterbone
12 жыл бұрын
How was the performance of each trial assessed?
@learnbydoing678
3 жыл бұрын
What is the reward function for the cart inverted pendulum system?
@user-lp8ij5bj8s
5 жыл бұрын
看起来效果很好。
@51nibbler
Жыл бұрын
perfect =D
@kennycorris
14 жыл бұрын
so...in essence this machine learned to swing and balance the arm on its own?
@CORNSTARCHinc
14 жыл бұрын
Other way and it would break. One of my professors showed us a video like this, and when he did it the other way, the machine didnt know that he was doing it in a different direction, that machine was a whole lot different, though. This one might be able to do it.
@henriknielsen408
2 жыл бұрын
Hello. Is it possible to find out which parts have been used for the mechanical
@randomguy3579
14 жыл бұрын
thats fucking cool
@guyboy625
11 жыл бұрын
Essentially it got rewarded based on its performance, which encouraged good behavior and discouraged bad behavior. In the end it was very well behaved because it applied all the behavior that gave it the reward.
@raghavenderemmadisetti6583
3 жыл бұрын
can i have the learning model where I can buy it
@joancollrubi8185
5 жыл бұрын
me he quedado anonadado
@udi0Point
13 жыл бұрын
proof of evolution
@misterlith
14 жыл бұрын
Any reason you only knock the pole down anti-clockwise?
@jasondowd3099
6 жыл бұрын
Yes, but how did you do it??
@juanfelipemontoya5821
4 жыл бұрын
hahahaha bro you hace to study control enginering and computer science for 7 years
@paugasolina5048
4 жыл бұрын
@@juanfelipemontoya5821 easy i already done it but dont need computer science, need engineering
@smoothoctopus
5 жыл бұрын
This is 10 years old, but hollly snap buddy fix your belts.
@IllSkillz
8 жыл бұрын
use PID for that king of tasks
@33mr17
7 жыл бұрын
reinforcement learning
@yousorooo
7 жыл бұрын
But you have to tune a PID controller manually while this is automatic.
Пікірлер: 34