Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Self-Parking Car Evolution

trekhleb.dev

Post reply on HN
Print view View original

31–40 of 45 posts

Re: Show HN: Self-Parking Car Evolution

#31

Post by riboflavin123 »

trekhleb wrote: post #9
riboflavin123 wrote: post #8

Earlier quoted context omitted.

The page says: > For better results, increase the population size to 500-1000 and wait for 50-100 generations Do you have example output from that? I'd expect my computer to take months of running 24/7 to get there.

Yes, you may press the "Restore Evolution" button (at the bottom of the screen) and then upload the pre-saved training checkpoints from here https://github.com/trekhleb/self-parking-car-evolution/tree/... You may also press the "Restore Evolution" button and then press "Use demo checkpoint" to use some pre-trained data.

Oh, amazing. Thanks!

Re: Show HN: Self-Parking Car Evolution

#32

Post by freediver »

Incredibly well explained, kudos to author! This reinvigorated my interest in genetic algorithms. Last time I considered getting my hands dirty with GA was for this Kaggle challenge which still remains largely unsolved:

https://www.kaggle.com/c/abstraction-and-reasoning-challenge

Re: Show HN: Self-Parking Car Evolution

#33

Post by macmmajorbtw »

endisneigh wrote: post #28

How challenging would it be to design something similar generically, such that you can just define the "pain" and "reward" and just have some random 3D model in a 3D world take random actions until there's no more "pain"?

What your describing is reinforcement learning :)

Re: Show HN: Self-Parking Car Evolution

#34

Post by endisneigh »

macmmajorbtw wrote: post #33
endisneigh wrote: post #28

How challenging would it be to design something similar generically, such that you can just define the "pain" and "reward" and just have some random 3D model in a 3D world take random actions until there's no more "pain"?

What your describing is reinforcement learning :)

Haha, sorry I meant specifically with 3D models like the OP.

Re: Show HN: Self-Parking Car Evolution

#35

Post by sbierwagen »

athorax wrote: post #26

Really enjoyed this bug haha: https://github.com/trekhleb/self-parking-car-evolution/issue... Auto manufacturers should just implement that behavior!

Reinforcement learning bots exploiting physics engine bugs has a long and illustrious history: https://arxiv.org/pdf/1803.03453.pdf https://news.ycombinator.com/item?id=16600701

Re: Show HN: Self-Parking Car Evolution

#37

Post by fxtentacle »

jetrink wrote: post #10
Someone wrote: post #6

> Whenever the sensor doesn't see any obstacles it reports the value of 0. On the contrary, if the value of the sensor is small but not zero (i.e. 0.01m) it would mean that the obstacle is close. I would guess that mapping ”nothing here” to a value that is higher than the others would give better results. The software wouldn’t have to learn that weird inversion where the safest value is very close to the least safe o…

Alternatively, it would be interesting to try having the sensors output 1/(distance + k), where k is maybe 0.1m. Then the output would naturally go to zero as things got further away.

Many depth estimation AI approaches do that and call it disparity. The idea there is that as things get further away, you'll see distances less precisely, so perceptually 20cm to 30cm might be the same as 20m to 30m

Re: Show HN: Self-Parking Car Evolution

#38

Post by andai »

trekhleb wrote: post #9
riboflavin123 wrote: post #8

Earlier quoted context omitted.

The page says: > For better results, increase the population size to 500-1000 and wait for 50-100 generations Do you have example output from that? I'd expect my computer to take months of running 24/7 to get there.

Yes, you may press the "Restore Evolution" button (at the bottom of the screen) and then upload the pre-saved training checkpoints from here https://github.com/trekhleb/self-parking-car-evolution/tree/... You may also press the "Restore Evolution" button and then press "Use demo checkpoint" to use some pre-trained data.

Does each visitor submit their dna back to the server? Using the power of the web this allows you to have as many "cores" as you have visitors, and train massively parallel!

Re: Show HN: Self-Parking Car Evolution

#39

Post by andai »

trekhleb wrote: post #21
criddell wrote: post #16

Earlier quoted context omitted.

Have you thought about a native version? I get the appeal of writing for the browser but it's so damned slow compared to what you could get natively.

I haven’t thought about the native version, it was fun trying to implement it for browser. To resolve the performance issue I would try next to switch to the 2D simulation engine, since we don’t use the height during the parking. Getting rid of the 3rd dimension, lights and complex geometry would increase the performance drastically I believe

And then still render it in 3D, right? That's a really cool idea.
Post reply on HN