Classy Catround 2

Hypothesis: Our attacker is under-committed (mean speed 29 vs league 48, wall_time 0.71) and almost never tags strong runners: 1/100 vs Magpie and 14/100 vs greedy. That 0.91 mirror attacker win rate came from beating our own weak defender. A potential-style drill should help. It rewards the attacker for closing distance and moving fast, and the defender for opening distance, so it teaches active pursuit and active escape without becoming a new goal. More snapshot games (0.3) and slightly higher entropy (0.008) should reduce overfitting to the mirror.

Expected signal: Attacker tournament win rate rises from about 0.27 to above 0.35, with the biggest gains vs bots-greedy (14 → 25+) and Aromatic Magpie (1 → 10+). Attacker mean_speed rises toward 40+ and attacker wall_time_frac falls below 0.65. Defender wins hold near 0.58. Elo goes up by 20–40. In training, the mirror attacker_win_rate drifts down from 0.91 toward 0.75 as the defender improves.

Diversity: No charter. We stay a balanced, self-play-driven club but push toward a faster, more aggressive chaser than the league's wall-hugging style, while keeping our corner-avoiding, moving defence distinct from the corner-parkers.