Nostrademous

@Lothrik we actually know the natural maximum of each gem. It's in the `src/Data/Gems.lua` file and for some reason called `defaultLevel` for each gem.

Tried that, no luck. ``` (env) nostrademous@DESKTOP-J9431IB:~/ML/deep-neuroevolution/gpu_implementation/gym_tensorflow$ make Traceback (most recent call last): File "", line 1, in AttributeError: module 'tensorflow' has no attribute 'sysconfig' Traceback (most recent call last):...

I did get the gym to compile after reinstalling the latest version of tensorflow (1.8.0) like I have with tensorflow-gpu. The previous 0.12 version was per the top-level requirements pip...

I know there is a model-free versus modeled env discussion to be had here, but wouldn't it be just much faster to encode all the trees? What you suggests with...

Threw this in a Think() function of a random bot: ``` function Think() for i=0,3000,1 do vloc = GetTreeLocation(i) print(i, vloc) end end ``` Read the console file... [console.4276350658.log](https://github.com/TimZaman/dotaservice/files/2688192/console.4276350658.log)

Created a new repo for dota world state handling with submodule of dotaservice (need to link things up still and document my proposed design), but on topic of Trees I...

By the way, I see that you are using "auto-generated files" as a means to communicate between the bots and the agent. This assumes they always exist on the same...

I'm fine with file passing providing it's "fast enough" which I believe it is. Back to the initial question though - as we slowly transition to 5 agents and self-play...

which library/executable did the "Init" reside in? I guess I'm asking if you know if the functions I am to find the signatures for exist in the main dota2 binary...

Observe(size_t teamID, void *, void *) First arg is team ID. 2 for Radiant, 3 for Dire. Busy with kids right now but I believe 2nd will be pointer to...