Happens any time you connect two bits with muscles and no bones to hold it. Apparently, even just connecting 2 bones with one muscle does it and can pass all the tests.
Recent community posts
The goal: One bot, 4 challenges.
-Can't be lame like 2 disjointed sticks connected to a muscle.
-Can't really be designed for any particular contest* (Had to tweak a few things to make the stairs work in the end, I've been at it for like 2 weeks, good enough lol)
-Needs to use 2 hidden layers, has muscles than require coordination to solve tasks
-Everything is the same besides the challenge. Same settings. Same brain. Same timeframe. Same everything.
I give you, Mr. Squiggles! Enjoy!
edit: hard to see, but it's 23 muscles, total of around 65 neurons (two hidden layers of 15 each). There are two layers of muscles. First, one connecting each bone to to the next to give it some structure, and then another one connecting every other bone for strength. Some of these muscles can contradict each other or have difficult to predict effects on each other, so the bot needs to fight itself to actually converge on something.
This was WAY harder than I thought. My own rules making it so much harder on myself than I needed to be. I never saw any late-game emergence. I've left it on overnight with different bots and different setups and basically been simulating one thing or another for about 2 weeks straight and I never saw any later-game emergence. Not saying it can't happen, but generally after thousands of generations, I've just gotten stuck in a rut.
The good news is, I didn't have to run these very long. I was able to get a nice satisfying video in 120 generations, or about 22 minutes. Not long term, but solved most of my criteria!
Thanks, great reply!
I will start playing with those options. I hadn't even changed those at all yet. Especially mutation rate, I wasn't exactly sure how that worked. I'll start with that one and start introducing the others over time.
I've cut the legs down a little bit and strengthened the core, too. Cut it down to 8 muscles. It's climbing the stairs right now. Exactly like I was hoping I did get it to go from consistently falling down the stairs to hanging on the edge. It looks like it *wants* to start hopping up. But it's been about 900 generations and I've only seen it jump a couple of times.
It's going to make a really cool video watching it grow in all 4 simulations at once.
I watched the same 3 blue 1 brown series mentioned in the FAQ last year and have been obsessed ever since. Love this app, so simple and perfect for experimentation. Thanks for putting it together!
Been playing around with this for a few days now. I want to build something that doesn't just hop in the right direction. I can let the thing run for days if I have to, I just want to see a really satisfying late-generation emergence. I understand there's going to be some limitations with this kind of a sim, but I'm willing to sacrifice a fair bit of processing time in the name of science! Lol
My goal is to make one design that accels at all 4 challenges without being a couple of sticks connected with one muscle. And I'd prefer it to have as little intentional form as possible. I've settled down on a design I called a daddy longlegs. A small square core with 4 squiggly legs. Total 12 muscles. It's just strong enough it can bounce around but floppy enough to catch the stairs after letting it fall to it's death a few hundred times. It's basically the spider with 4 legs that are basically 2-muscle springs.
I'm having some success, enough that it seems promising, but after a while, I'm really not sure if it's getting better or not. So...
1) have you ever seen something appear *almost* dormant for a while and eventually had a breakthrough, or does that generally mean it's done learning?
2) let's say it's done learning, what factors can potentially get past that? Even if I don't mind letting it run overnight for a week.
So far, I've:
Increased population size to 1000, batches of 25.
Set initial period to 2 seconds until most bots were jumping in the right direction, then increased by a couple of seconds, etc.
I've kept the best bots most of the time, but when one bit ends up totally separate from the pack, I "prune" it.
I saw a ton of progress up to generation 50, but left it overnight and basically saw no progress at all. Re-did it without keeping the best not and it maybe looks like it's standing on its feet more consistently, it's not getting more than a couple of hops and nothing hops past the initial time period at all (ie, no sustained movement, just better initial conditions)
Is it possible it will actually walk at some point? Would increasing brain size help at all? Currently it's 43 nodes: 11/10/10/13.
I'm not too too worried about overfitting a little bit because I want to put them all in one video so you can see it evolve differently in each situation. So if I just means 10 times more computational time but has a chance to eventually converge, I'm down for it.
Or is it just not gonna happen?