Train AI in Godot (Tutorial)

Train reinforcement learning agents in Godot with Godot RL Agents. 0:00 Intro 0:18 How it works 0:35 Warning 0:56 Setup: Python side 1:34 Setup: Godot Side 3:43 Installing & Using the Godot addon 5:47 Testing the AI 7:00 Speeding up the training process 7:45 Exporting the AI model 9:34 Exporting the game (not directly shown) There probably are a lot of errors in the video, so please tell me if anything is wrong. Godot RL Agents https://github.com/edbeeching/godot_rl_agents Godot Addon https://github.com/edbeeching/godot_rl_agents_plugin Example Python script used for training https://github.com/edbeeching/godot_rl_agents/blob/main/examples/stable_baselines3_example.py ONNX Runtime https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime Docs https://github.com/edbeeching/godot_rl_agents/tree/main/docs Examples https://github.com/edbeeching/godot_rl_agents_examples Godot RL Agents Discord https://discord.gg/HMMD2J8SxY Exporting for macOS The first issue is possibly related to this. https://github.com/microsoft/onnxruntime/issues/9707 Workaround: Place libonnxruntime.dylib in the appname.app/Contents/Resources/data_appname_arm64 The second issue is that it can't detect the onnx file. The issue is unclear. Workaround: Enter the absolute path of the onnx file to the sync node.