Correct the exploiter budget: it was a quarter of the target, not half

The exploiters ran 32.5M learner actions, not the 65.5M I recorded -- they train
one seat, so a 250x1024 run yields half of what the same shape gives the
both-seat self-play trainer. Against targets trained on 131M and 122.6M, that
makes the attacker roughly 4x underfunded.

Which means the absolute number does not support "ours is only 22.8%
exploitable". It supports exactly one claim: at a matched budget, league gives up
more. Whether the ordering survives a properly funded attacker is now the open
question, so the script takes --updates and --batch-games to run it.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XBQKgvBbxbheiTF1AVy1Sh

scripts/measure_exploitability.py

@@ -8,6 +8,7 @@ frozen policy could not defend.
 
 from __future__ import annotations
 
+import argparse
 import json
 from pathlib import Path
 
@@ -77,6 +78,12 @@ def _final_score(cfg, exploiter_params, frozen, matches: int) -> dict:
 
 
 def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--updates", type=int, default=250, help="exploiter training updates")
+    parser.add_argument("--batch-games", type=int, default=1024)
+    parser.add_argument("--tag", default="", help="suffix for the run dir, to keep runs apart")
+    args = parser.parse_args()
+
     match_cfg = load_config("configs/jax_ppo/match-selfplay.yaml")
     old_cfg = load_config("configs/jax_ppo/balanced.yaml")
 
@@ -94,10 +101,10 @@ def main() -> None:
     for name, frozen in targets.items():
         print(f"\n===== training an exploiter against: {name} =====", flush=True)
         cfg = load_config("configs/jax_ppo/match-selfplay.yaml")
-        cfg.ppo.batch_games = 1024
-        cfg.run.total_updates = 250
-        cfg.run.log_every = 25
-        slug = name.split()[0]
+        cfg.ppo.batch_games = args.batch_games
+        cfg.run.total_updates = args.updates
+        cfg.run.log_every = max(1, args.updates // 10)
+        slug = name.split()[0] + args.tag
         state = train_exploiter(cfg, frozen, Path(f"runs/jax-ppo-match/exploit-{slug}"))
         result = _final_score(cfg, state.params, frozen, MATCHES)
         rows.append({"target": name, **result})
@@ -110,7 +117,7 @@ def main() -> None:
         ci = f"[{row['wilson_low']:.3f}, {row['wilson_high']:.3f}]"
         print(f"{row['target']:<28}{row['exploiter_win_rate']:>20.4f}{ci:>22}")
     print("\nhigher = the frozen policy had more to farm. 0.5 = nothing found.")
-    Path("runs/jax-ppo-match/exploitability.json").write_text(json.dumps(rows, indent=2))
+    Path(f"runs/jax-ppo-match/exploitability{args.tag}.json").write_text(json.dumps(rows, indent=2))
 
 
 if __name__ == "__main__":