feat(*): Add self-play RL training pipeline with PPO trainer, in-game GDScript policy inference, and bot opponent support in Match mode

This commit is contained in:
Josh Creek
2026-07-18 19:32:51 +01:00
parent 328831df1f
commit 85f96eb15e
81 changed files with 3934 additions and 10 deletions
+3
View File
@@ -0,0 +1,3 @@
Vendored from https://github.com/edbeeching/godot_rl_agents_plugin
commit 998c357a0cd09b37f40a36d70c7867fc9f682338 (2026-06-13), MIT license (see LICENSE).
The onnx/csharp files are unused (require the .NET Godot build); in-game inference uses scripts/policy_network.gd instead.