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.md

@@ -122,8 +122,8 @@ appends to `training/eval_history.json` — the long-term progress record.
 Evaluate each new candidate against the previous promoted bot and a fixed
 early reference to see absolute progress over time.
 
-If a model was trained with the locomotion mask on (curriculum stages 1-2 —
-see below), pass `--grounded-a`/`--grounded-b` for whichever side it's on.
+If a model was trained with the locomotion mask on (curriculum stages 1, 2,
+and 5 — see below), pass `--grounded-a`/`--grounded-b` for whichever side it's on.
 The eval otherwise runs `AIShipController` fully unmasked regardless of how a
 model was trained, so a grounded model's untrained vertical/pitch-roll output
 reaches the ship as noise it never had to contend with during training —
@@ -159,22 +159,40 @@ just with different curriculum flags.
 | 2 — defend too | `--opponent-mode self_play --no-allow-vertical --no-allow-pitch-roll` | Reintroduces a live opponent (self-play) and the default episode-start mix — the same near-goal state is now simultaneously a finishing chance for one side and a defensive save for the other. Locomotion stays grounded. |
 | 3 — no draws | `--draw-penalty 5 --reset-std 0.3` | Training episodes are golden-goal (end at the *first* goal), so there's no in-episode goal-margin to penalize — `draw_penalty` is the closest available signal: a one-time penalty when an episode times out with no goal at all, on top of the existing per-tick `time_penalty`. Also lifts the locomotion mask (full 3D controls) by omitting `--allow-vertical`/`--allow-pitch-roll`; pair that with `--reset-std` since the policy never got a reward gradient on those axes before now, so expect a brief re-exploration wobble. |
 | 4 — mechanics/refinement | *(no curriculum flags — plain `next_run.sh`)* | Stock self-play, full controls, default reward/start-state mix. This is what all runs before this feature already did. |
+| 5 — aggression | `--opponent-mode self_play --no-allow-vertical --no-allow-pitch-roll --velocity-to-ball-weight 0.05 --ball-distance-penalty 0.006 --ball-touch-reward 0.5` | **Resumes from stage 2 (`curric-s2-defend`), not stage 4** — see the regression note below. Retunes ball-pursuit reward weights (up from 0.02/0.002/0.4) for much more aggressive, constantly-chasing floor play, deliberately keeping the locomotion mask on so it can't reopen the stage-3 regression. |
+
+> **Stages 3-4 regressed and are parked.** The locomotion-mask inference bugfix
+> (`8c15c46`) revealed that stage 3's evals up to that point had been running
+> with an unfairly unmasked grounded reference. Re-evaluated fairly,
+> `curric-s2-defend` (grounded) beats both `curric-s3-no_draws` (26-60) and
+> `curric-s4-mechanics` (24-57) — lifting the locomotion mask to full 3D in
+> stage 3 was a clear regression in floor play that self-play never earned
+> back. Stage 5 sidesteps this by resuming and evaluating against stage 2
+> directly (`curriculum.py`'s `resume_from_experiment`/`reference_experiment`
+> stage-dict overrides) instead of chaining through stages 3-4. Full 3D
+> flight is parked as a separate initiative — see TODO.md — that will need a
+> redesigned unmasking approach (more timesteps and/or reward rebalancing) so
+> it doesn't cost floor fundamentals again. See `curriculum_state.json`'s
+> stage-2/stage-3 log entries for the full eval numbers.
 
 All curriculum flags default to leaving Godot's own `@export` defaults
 alone (`train.py` only forwards a flag when you pass it), so ordinary runs
 are unaffected. Full flag list: `--opponent-mode {self_play,inert,frozen}`,
 `--opponent-model <path>` (for `frozen`), `--draw-penalty`,
 `--attack-goal-bias`, `--kickoff-chance`, `--near-goal-chance`,
-`--allow-vertical`/`--no-allow-vertical`, `--allow-pitch-roll`/`--no-allow-pitch-roll`.
+`--allow-vertical`/`--no-allow-vertical`, `--allow-pitch-roll`/`--no-allow-pitch-roll`,
+`--velocity-to-ball-weight`, `--ball-distance-penalty`, `--ball-touch-reward`.
 
 ### Running it automatically
 
 `training/curriculum.py` (started via `curriculum.sh`, same detached-tmux
-pattern as `start_training.sh`) drives all four stages end to end: for each
+pattern as `start_training.sh`) drives all stages end to end: for each
 stage it runs `run_training.sh` (pull, train, export, commit+push) with that
 stage's flags, then evaluates the resulting checkpoint against a reference
-bot — the fixed `rookie.json` baseline for stage 1, or the previous stage's
-promoted checkpoint for stages 2-4 — over 100 episodes.
+bot over 100 episodes — the fixed `rookie.json` baseline for stage 1, the
+previous stage's promoted checkpoint by default for stages 2+, or an
+explicit `resume_from_experiment`/`reference_experiment` override in that
+stage's dict when it deliberately skips a since-regressed branch (stage 5).
 
 ```bash
 cd training