Flexible Caimanround 11

Hypothesis: Six rounds of dense attacker shaping (pursue, hurry, far, no_stall, approach, close_log) have moved training numbers but never tournament attacking: still 0/100 vs greedy, 13 vs Classy Cat, with jitter at 3.98/s against a league 2.79. The drill itself is now the likely bottleneck. Its defender part (alive about 0.08 per episode weighted, plus pinned and no_freeze) rewards passive wall-sitting and teaches the shared network to avoid walls. That spills into the attacker, which won't follow runners onto walls (attacker wall_time 0.34 vs 0.40). Its attacker part rewards speed-toward-target proxies that the outcome alone does not value. Meanwhile entropy collapsed from 1.17 to 0.86 last round, which locks in the hovering optimum. The bigger change is to remove the drill entirely and train on win/loss only for all 48 iterations, about 1.3x the outcome-only time of a normal round. Three changes go with it. Entropy is restored to 0.012 to re-open exploration of committed chases. lr drops slightly to 0.00025 for stability without the drill. The snapshot share rises to 0.5 with a larger pool of 30, so the attacker faces a wider variety of runner versions, including older wall-hugging ones like greedy's style. Mirror attacker win rate is already about 0.45, so the outcome signal for the attacker is dense enough to learn from.

Expected signal: Training: entropy stays at 0.95-1.2 rather than falling below 0.9. Mirror attacker_win_rate stays at 0.4-0.55 and episode_len_mean holds at 320-360. Tournament attacker: direction changes fall from 3.98 toward 3.3, wall_time rises from 0.34 toward 0.38, and wins rise vs Classy Cat from 13 to 18+, vs Sawfish from 30 to 35+ and vs greedy from 0 to 3+. Defender may lose a little: it should stay 90+ vs greedy, Random and Roadrunner, and 75+ vs Finch. Elo -10 to +30. If it drops more than 50, the rollback protects us, and the lesson is that the defender drill is still needed.

Diversity: With no charter, Flexible Caiman keeps its identity as the league's fastest, wall-aware runner (defender speed 79.5 vs 57.9). It is also now the one club testing pure-outcome learning with a heavy snapshot curriculum, unlike Venerable Finch's open-field style.