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

2026-09-10 16:04:04 +00:00 · 2026-07-18 19:32:51 +01:00
parent 328831df1f
commit 85f96eb15e
81 changed files with 3934 additions and 10 deletions
@@ -1 +1,8 @@
-.DS_Store
+.DS_Store
+
+# RL training artifacts (training/ code is committed; outputs are not)
+training/.venv/
+training/logs/
+training/checkpoints/
+training/smoke_run.log
+training/__pycache__/