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

2026-09-15 03:12:03 +00:00 · 2026-07-18 19:32:51 +01:00
parent 328831df1f
commit 85f96eb15e
81 changed files with 3934 additions and 10 deletions
@@ -0,0 +1,5 @@
+godot-rl
+stable-baselines3
+tensorboard
+# Optional, for --wandb logging:
+# wandb