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

Game/scripts/ai_ship_controller.gd

@@ -0,0 +1,90 @@
+class_name AIShipController
+extends ShipController
+
+# Drives a ship from a trained self-play policy (see TRAINING.md). Builds the
+# same canonical observation as training (ShipObservations) and runs the
+# policy MLP in GDScript (PolicyNetwork) — the shipped bot has no Python,
+# .NET, or network dependency.
+#
+# Difficulty is (model, reaction_ticks, action_noise): weaker checkpoints make
+# easier bots outright, and the two knobs handicap a given model further —
+# slower reactions and noisier execution. Models live in res://bots/.
+
+@export_file("*.json") var model_path: String = ""
+# Decide a new action every N physics ticks, holding the last one between
+# decisions. 8 matches the training action_repeat; larger = slower reactions.
+@export_range(1, 60) var reaction_ticks: int = 8
+# Uniform noise magnitude added to each action axis (0 = play at full skill).
+@export_range(0.0, 1.0) var action_noise: float = 0.0
+
+var _policy: PolicyNetwork
+var _action := ShipAction.new()
+var _ticks_until_decision := 0
+
+var _ship: Ship
+var _opponent: Ship
+var _ball: RigidBody3D
+var _attack_goal_position: Vector3
+var _scene_refs_ready := false
+
+
+func _ready():
+	if not model_path.is_empty():
+		_policy = PolicyNetwork.load_from_file(model_path)
+
+
+func get_action() -> ShipAction:
+	if _policy == null:
+		return _action  # unloaded model: behaves like the inert placeholder
+	if not _scene_refs_ready and not _discover_scene_refs():
+		return _action
+
+	_ticks_until_decision -= 1
+	if _ticks_until_decision <= 0:
+		_ticks_until_decision = reaction_ticks
+		_decide()
+	return _action
+
+
+func _decide() -> void:
+	var obs := ShipObservations.build(_ship, _opponent, _ball, _attack_goal_position)
+	var out := _policy.forward(obs)
+	# Output layout matches the flattened training action space (Box(7)):
+	# thrust xyz, rotation xyz, turbo (> 0 means on).
+	_action.thrust = Vector3(
+		_axis(out[0]),
+		_axis(out[1]),
+		_axis(out[2])
+	)
+	_action.rotation = Vector3(
+		_axis(out[3]),
+		_axis(out[4]),
+		_axis(out[5])
+	)
+	_action.turbo = out[6] > 0.0
+
+
+func _axis(value: float) -> float:
+	if action_noise > 0.0:
+		value += randf_range(-action_noise, action_noise)
+	return clampf(value, -1.0, 1.0)
+
+
+# Find ship/ball/opponent/goal once everything is spawned. ShipAction axes
+# are body-frame so only observations need team context (ShipObservations).
+func _discover_scene_refs() -> bool:
+	_ship = get_parent() as Ship
+	if _ship == null or not is_inside_tree():
+		return false
+	_ball = get_tree().get_first_node_in_group("ball")
+	for node in get_tree().get_nodes_in_group("ship"):
+		if node != _ship:
+			_opponent = node
+			break
+	for goal in get_tree().get_nodes_in_group("goal"):
+		if goal.team == 1 - _ship.team:
+			_attack_goal_position = goal.global_position
+	if _ball == null:
+		return false
+	_scene_refs_ready = true
+	return true