Ivan-267

Opened so we can track and discuss @edbeeching's idea https://github.com/edbeeching/godot_rl_agents_examples/pull/19#issuecomment-1886444206: > Perhaps we can think of a better way to store the training parameters so that new users can have...

Adds the ability to resize the image before sending it to the Python server.  Briefly tried on the VirtualCamera example. Setting a high image render resolution will have a...

This branch was made to show one possible way to refactor AIController to address some ideas mentioned on Discord. It hasn't been well tested yet. Feedback, suggestions, alternatives to the...

Changes to enable discrete actions > 2

8

Experimental changes to enable discrete actions > 2 using SB3 (during training and with exported onnx). This also requires the changes in the main repository to work: https://github.com/edbeeching/godot_rl_agents/pull/121

Fix for Windows training

2

I was able to start Sample Factory training on Windows 10 64 bit using the following: - First installing the PR branch for signal slot that allows installation on Windows:...

Fix for non-uniform grid sizes.

Adds the RobotFPS example

3

## RobotFPS environment: An arcade style FPS environment, trained using SB3 PPO, observations contain 3 stacked frames of data from a raycast sensor (extended to add the facing direction of...

Cooperative environment, in order to get the ball into the goal, players must cooperate as only one player is allowed to hit the ball at a time (the white dot...

This PR Adds the 2DTerrainChallenge env. https://github.com/user-attachments/assets/54bf4298-832c-48c3-a20c-a2d395a5cf06