AI Learns To Swing Like Spiderman

preview_player
Показать описание
J Jonah Jellynose suspects Spiderman is an AI. Captain Blubber is arrested twice. A phone screen is smashed. What is happening

0:00 Intro
0:30 Basics
1:30 States, Actions and Rewards
2:45 Discount Factor
4:09 Neural Networks
5:59 PPO
7:03 Policy Gradient
9:54 Clamping the Policy
10:34 What the AI Learned
13:05 Just Swinging

White paper on how to create an AI like this from scratch:

Useful Links:
Рекомендации по теме
Комментарии
Автор

I love how chill and lazy the AI Spiderman seems. It's like Spiderman putting the least effort into moving about with his webs, whilst allowing his body to just ragdoll with it all.

skycloud
Автор

I like how the AI just resorts to using one hand form web shooting once it gets going. It’s like “why do I need two hands to shoot seems like a waste”

AlliSinned
Автор

because of the spiderverse this is a canon spiderman

Smightr
Автор

I think the reason the ai moved to using only one hand was to minimize the randomness that happens to its decisions. Since half the time they don't affect the outcome if you don't use one of them.

Music-nnmi
Автор

ten years ago i would not imagine myself sitting here eating my food while watching an AI grow up to be spiderman

roscoe
Автор

13:06
- he almost fell done
- saved himself in the last second
- celebration backflip

yudoball
Автор

It's ironic because in most spider-man games, quick "thwips" are usually faster than using full swings, as you keep momentum better. Long swings have a curve to them and usually take a bit longer than just jumping off at the apex, which essentially looks like you are only swinging half way before thwipping again. It seems the AI has learned this.

mitrikgaduk
Автор

12:48 “It’s so good in fact, that it doesn’t need to look where it’s going” It developed Spidey sense without any programming lmao 😂

Amyroselee
Автор

"With great distance, comes great rewards" - Piderman

thatflatdude
Автор

5:54 Does this mean you could teach a jellyfish to be SpiderMan 10 times faster than this computer?

Teslijah
Автор

Let’s just sit and applaud the fact this man can code this stuff, animate fun stuff, and WRITE what happens in a coherent way for new people

Holy crap 👏👏👏👏👏👏👏

ironicanimations
Автор

10:52

Seizure man, Seizure man
Has a seizure when he can
Lights a flash, he's collapsed
Epileptic on the task

itsazh
Автор

I love how the web-slinging sound is just you going _"chu" "shue" & "shu"_

TheActualAnthonino
Автор

I love how occasionally it does a spider-man like trick or flip, but for the most part it just like flails around and lets gravity have its way.

TheFrozenFlame
Автор

I like how it uses little micro-adjustments like you would do with thrusters in space. It's cool to see it so casually correct its course.

drphalanges
Автор

A thousand times, thank you for the segment at the end following the trained model! It is SO frustrating when a channel explains something for ten minutes, and then instead of giving you the gratification of a finished product (something I'm sure the creator enjoyed plenty of) they just end off with "whelp thanks for watching!

shufflecat
Автор

I'd love to see a part 2 to this that attempts to make variants by adding silly additional rewards (aka reinforcement learning) to the current spiderman, like a version that tries to do as many backflips as possible whilst also going fast in a forwards direction.

PercentImagination
Автор

This is very good
appreciate the swinging bit at the end, but also for providing a full explanation
a bunch of youtubers I've watched will start out explaining something then blur all the words together to make it seem uber complex, and then skip right to the final product without actually explaining the steps they took to get there

DarkTakanuva
Автор

I'd like to see this with more constraints added (such as web cooldown, web transit time, Spider-man needing to see where he's going instead of flopping around, how body position effects momentum, etc).

Kaylakaze
Автор

I learned more in 15 mins here than I did in a semester of Reinforcement Learning. Maybe not, but this one is a lot simpler and visually statisfying

BenSuzuki