Ariel Flesler
Ariel Flesler
+1, determinism is a plus and I see no downside
I would say that just adding something like a `synaptic.random()` that returns `Math.random()` and using it everywhere, will let "us" override it any way we want. That seems simpler and...
Is this something like poker? Or that one can be solved by trying all possible opponent cards?
Maybe this helps. Here's a pretty simple example of a server and browser workers that receive a large list of numbers and return some back. https://github.com/wagenaartje/neataptic/tree/master/src/multithreading/workers
Right, also the states are potentially large JSON objects, not just arrays of numbers or bytes that you can optimize for. It's a hard one now that I think of,...
I really like this project, specially the simplicity of it. Hope you can make it able to handle more cases
I've been experimenting with NN and Neuroevolution for AI and discovered this library (not related to ML I know). So I want to try it for some cases, the first...
I think the problem is you are executing the WHOLE string as command. The example above doesn't quite make sense, it seems like it's running a single command. This tool...
Seems like the environment doesn't have NPM
@KoljaB this PR is very messy. But it'd be nice to have access to `task` (and maybe a few others). It's mostly a pass-through. When using a multilingual model, it...