fix(training): correct stage-3 eval (locomotion-mask bugfix) and add grounded aggression stage

Re-ran stage-3 (curric-s3-no_draws vs curric-s2-defend) and the missing
stage-4 gate now that the locomotion-mask inference bugfix is in. Both
reverse or contradict the pre-fix bookkeeping: curric-s2-defend (grounded)
beats curric-s3-no_draws 60-26 and curric-s4-mechanics 57-24 when fairly
evaluated, so lifting the locomotion mask in stage 3 was a real regression
in floor play, not the improvement the buggy eval reported.

Adds a stage-5 "aggression" curriculum entry that resumes from stage 2
directly (via new resume_from_experiment/reference_experiment stage-dict
overrides in curriculum.py) instead of compounding the regression through
stages 3-4, keeps the locomotion mask on, and retunes ball-pursuit reward
weights for much more aggressive floor play. Extends train.py with the
three new --velocity-to-ball-weight/--ball-distance-penalty/--ball-touch-reward
flags needed to forward that retune to Godot's existing SHIP_AI_OVERRIDES.

curriculum_state.json and TRAINING.md are corrected/annotated in place
rather than silently rewritten, so the regression stays visible in history.

training/train.py

@@ -84,6 +84,18 @@ def parse_args():
         default=None,
         help="Allow pitch/roll rotation (default true)",
     )
+    curriculum.add_argument(
+        "--velocity-to-ball-weight", type=float, default=None,
+        help="Overrides ShipAIController.velocity_to_ball_weight (dense reward for closing speed toward the ball)",
+    )
+    curriculum.add_argument(
+        "--ball-distance-penalty", type=float, default=None,
+        help="Overrides ShipAIController.ball_distance_penalty (dense per-tick cost scaled by distance to the ball)",
+    )
+    curriculum.add_argument(
+        "--ball-touch-reward", type=float, default=None,
+        help="Overrides ShipAIController.ball_touch_reward (event reward on ball contact, cooldown-gated)",
+    )
 
     return parser.parse_args()
 
@@ -101,6 +113,9 @@ def _curriculum_kwargs(args) -> dict:
         "ball_near_goal_chance": args.near_goal_chance,
         "ai_allow_vertical": args.allow_vertical,
         "ai_allow_pitch_roll": args.allow_pitch_roll,
+        "ai_velocity_to_ball_weight": args.velocity_to_ball_weight,
+        "ai_ball_distance_penalty": args.ball_distance_penalty,
+        "ai_ball_touch_reward": args.ball_touch_reward,
     }
     return {key: value for key, value in mapping.items() if value is not None}