Venerable Finchround 10

Hypothesis: Round 9's open-field and room runner works: defender time_to_tag is 17.5 s, and defender wins recovered vs Magpie (59) and held vs Pegasus (72) and Caiman (69). The chaser is now the weak side. It won only 16 vs bots-greedy, 21 vs Cat and 32 vs Pegasus, and training ended with attacker_win_rate 0.18. The mirror tilted to the runner because the chaser's only drill term is the telescoping closing term. That term nets to about 0.3 per episode, while the runner's open and room terms earn tens of units per episode. Add an attacker-only 'press' term that mirrors the runner's room term: it rewards each step spent close to the runner (within 200 u). The chaser should then learn to stay on the runner and drive at it rather than drift. Runner terms stay exactly as in round 9, so the defender comparison stays clean. Entropy rose to 1.5, and both roles jitter (4.5 and 5.1 direction changes/s). Lower entropy_coeff back to 0.01 to sharpen decisions and cut jitter. Snapshot settings are unchanged.

Expected signal: In UTC 10, attacker wins rise vs bots-greedy (16 to 35 or more), Pegasus (32 to 45 or more) and Cat (21 to 30 or more). Attacker mean_distance falls below 115 and attacker time_to_tag stays at 8.5 s or less. Attacker direction_changes_per_sec falls below 4.0, and defender's below 4.7. Defender wins stay within about 10 of round 9 vs Magpie, Pegasus and Caiman. Training attacker_win_rate ends between 0.3 and 0.5, and end entropy is about 1.0-1.3. Elo +15 to +50. If the defender collapses, press is shifting the mirror too far, and I would halve its weight.

Diversity: Finch stays the open-field club: low wall and corner time as runner (0.34 and 0.024 vs league 0.59 and 0.13). It now adds the charter's straight, persistent chaser, which stays on the runner rather than taking short, failed chases.