Ivan-267

> @Ivan-267 What is the current state of the PR? Any chance we can clean up the mess I have made? :D I am still using a variant of this...

Superseded by https://github.com/edbeeching/godot_rl_agents/pull/181. The branch can still be kept for reference since this implementation has an advantage, it sends only action values for discrete actions (not logits), so it could...

This is currently in progress: https://github.com/edbeeching/godot_rl_agents_examples/pull/14#issuecomment-1837311171 This should fix the sensor for Godot 4.2 so it works during training. What will still be left is to look into: - [...

Those were just some proposed options, none are implemented yet. I've tried the sensor a bit after writing those and I can confirm that we can't export onnx / run...

> This requires adding `getpass` to dependencies right? > > Can we instead use try/catch on `pwd.getpwuid` and if it fails use `import getpass; return getpass...`? I think `getpass` comes...

Thanks for this request. It seems we have it here now: https://github.com/edbeeching/godot_rl_agents/blob/main/docs/TRAINING_STATISTICS.md Although adding this link to the quick-start guide or one of the advanced tutorials might be useful.

One suggestion until/for **1.0** (not necessarily 0.9) is to extend the API with terminated/truncated and set the default AIController timeout restart to truncated, as it might have an effect on...

> Add an example with an agent interacting in a discrete environment, I am not even sure if this would sync correctly, needs testing. We now have an example of...

> @Ivan-267 Nice env! I love the idea. Just a suggestion, can you add a few maps instead of just one. I tried the FPS example, and found it quite...

Regarding the main readme videos, I'll arrange those before merging the new envs, since it needs to be done in order of merging.