Jan Kaniewski

Keep in mind that I'm not machine learning expert and you may need look up some more recent resources for best practices. A typical reinforcement learning method is Deep Q...

Saving and loading are largely vanilla tensorflow functions, please see e.g. https://www.tensorflow.org/tutorials/keras/save_and_restore_models for guides. See also this related stack overflow question: https://stackoverflow.com/questions/46514138/tensorflow-attempting-to-use-uninitialized-value-w-in-a-class

I think this is largely down to how the UE4 textures are being generated for inference. In simple terms the keyboard testing images are just images that were drawn in...

I'll try to look incorporate a more modern example/tutorial when the ML-remote upgrade is complete (may be a bit of time though). I'm a big fan of plug n play...

You can check out the old qlearning branch examples for in the loop communication: https://github.com/getnamo/tensorflow-ue4-examples/blob/qlearn/Content/Scripts/PongAI.py The basics of it is call a json input with your ai input e.g. wheel...

Convert your input to json and reshape the inputs into the size/dimensions your network expects. There's a handy struct to json string converter which can be used to feed the...

I'm not an expert at ML and I'm assuming you're asking the question of how to handle the environment part. With that in mind: The approach depends on complexity of...

use this release: https://github.com/getnamo/tensorflow-ue4/releases/tag/0.9.3 and try again. Packaging has just been mostly fixed. You may need to delete site-packages before you package and copy those over manually but it will...

I uploaded a new version of examples (0.4.1) and tensorflow release. Please use the [v0.10.1](https://github.com/getnamo/tensorflow-ue4/releases/tag/0.10.1) plugin release, if you get errors this time, consider posting the build logs found in...

On first run in a packaged setup it will reinstall pip and pull the dependencies. From your log I can see it successfully did this. All you should need to...