Welcome to Smogon! Take a moment to read the Introduction to Smogon for a run-down on everything Smogon, and make sure you take some time to read the global rules.
Whoops, I meant it this way around :bloblul:
Basically, there's a lot of different ways of exploring the game tree and using that information to predict the next best step to take. Your approach is fine (actually I don't 100% know what exactly your approach is), but essentially it's inefficient...
Just wanted to say i did my PhD in video-game AI and I think this is a really cool project; if you've got any questions I'd love to hear them! (Plus I might be able to spare some compute to run some training / simulating.)
Although it sounds like you're moving away from the Neural Networks...
What project are you working on? I have been doing a lot with permutation-invariant networks myself.
The embedding shouldn't be too hard to do. Just trawl through your dataset, and for each 'Mon, add it to a dictionary. Then you can just assign a cardinal number to each Mon based on its place...
Good work, I just have a couple of suggestions:
1.) You want to use a perutation invariant structure for your network, since the order of the pokemon doesn't matter.
eg. a teamsheet of the following:
1. Abra
2. Beldum
3. Chansey
4. Drapion
5. Exeggutor
6. Finneon
is the same as
1. Finneon
2...
A long long time ago I did a softboiled Clefable breeding project on emerald for DPP. By standards of today the result was crap, but I'm considering trying to RNG a better one and then bring it forwards.
How common are softboiled Clefables on here? Not sure I can be bothered if there's already...
would anyone be interested in a quick lookup table for IV inheritance BTW (or a guide for how to do the calculations in your head)? All it would take is a quick think about how to compact the data.
I don't know how many people breed without acess to the internet.
Well, unless you want to go catch a whole bunch of stuff I think you'll just have to see what you already have. Unless you're asking if anyone has something that fits the bill.
I tend to find that inheritance spreads without a 30 or 31 (or 0) are seldom worth worrying about too much.
Maybe look in your friend safaris to have a look if there's anything good. (Also check if the X is odd or even).