The games freezes some seconds every few minutes. After investigations, it seems that the LUA's garbage collector blocks the game. I've not that much mods... I tried and remove nearly each of them and nothing changed. Maybe too much robots? It didn't do that with more robots than that, before... I t...

This mod greatly enhance the AI. But imho you could have the groups going where few of them have died... So it would search for weaknesses... Like recon with small biters... And then attack with big groups where it's found to be less defended. So they would change their points of attack. Now they at...

I removed the ALT shortcut, anyway it's useless.

Worker bots and specialized roboports Workers bots which could harvest trees or ores, using pickaxes. What ? The idea is to have a class of workers bots, working around a robotic mine (a specialized roboport) when harvesting ore or a around a lumber mill when harvesting wood. The number of workers ...

Two rows of values: one is coming from outside to get "values", another to get "multiplicators". The output multiply the member of each set with its multiplicator and sums it. Simple. Multiplicators can be locked or not. Backpropagation is when the multiplicators are modified by ...

Actually I quite agree with my fellow moderator who moved your topic for two reasons. First is that there isn't really anything close to a true suggestion in the cry for help your post is. Second is that despite what you may think, thetrain signalling is that kind of easy to understand, hard to mas...

Recipes changes are awesome: kind of adaptability test. I think it should even be in the game by a way or another. Like at some point in the game, some of them should become obsolete, or technical progress would change the proportion of ingrediients needed. So it would be challenging to make an auto...

TL;DR

Steampunk look

What ?

Brass, old taps buttons and analogic displays and so on everywhere Make biters look like old SF monsters. Just graphics skins.

Why ?

It would be totally inline with the spirit of the game and it would enhance visual contrast. And fun

How you'd modify the weights to make it learn, I have no idea. I never managed to get my head around that aspect of neural networks. Maybe you can have a set of value that represent the travel time of a train like iron ore. Your neural network could be oriented to call train from the location that ...

+1

There could be also a count of damages done by each ennemy type in the last attacks, used as a modifier for the probability of this type to be spawned for the nexta attack, increasing the proba for the bests and thus their number in the next swarm. The size of the swarms could be modfied too by the ...

+1 It looks like a bug that it doesn't.

it might not be necessary [...] If your neurons are essentially multiply, sum, and branch, then I can't see why you couldn't do an integer-only implementation. Use 8-bit values for input and weight, get a 16-bit result from the multiply, maybe get a 20-bit result from the sum (assuming 16 inputs) a...

I think you could actually do this with the existing circuit network. I think Factorio's circuit network might be Turing Complete, though. It's got conditional branching out of the box, and you can build memory cells out of arithmetic combinators, though it is clunky. I agree. The point is to have ...

Would you want a realist Tetris? If you want a big factory you need "poor" graphics. Factorio is about efficience, not about realism. Visual effects aren't the game. Calculating rotations and raytracing takes a lot of time. Factorio massively uses short tables of precalculated values, dram...

i've never have so much time to see them but dead. Anyway they could be lamas, giant tartigrads, or vegetables. Spiders being probably the best choice :) anyway it's "skinnable". For the questions about gravity, anyway this planet has been terraformed at some point in the past, as it has t...

TL;DR Neural logic: [element of] neural networks. What ? I suggest a component that would read two sets of real values, the first being multiplicators for the second, which would be added. And result in an output. The next level of these components would be layers of neurons. The smaller the best. ...