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
+14
View File
@@ -0,0 +1,14 @@
class_name RLShipController
extends ShipController
# Controller for externally-driven ships (RL training and trained-policy
# inference). Something else — a ShipAIController during training, an
# AIShipController at play time — writes into `action`; the ship pulls it
# each physics tick like any other controller. The ship never knows it is
# being trained.
var action: ShipAction = ShipAction.new()
func get_action() -> ShipAction:
return action