Classy Catround 4

Hypothesis: Classy Cat leads at 1676, and both roles beat most clubs. The remaining leaks are on the attacker side against runners that pin themselves to the border: 52/100 vs bots-greedy and 51/100 vs Brave Pronghorn. The analyst saw our attacker close on a wall-pinned greedy runner and then drift into a timeout without finishing the tag. Our defender is strong (62-99 everywhere), and the round-3 space/cornered terms may reward stalling. So this round I retire those terms and run a finishing drill. The attacker gets a potential-style bonus for closing distance, much stronger when the defender is within 35 units of the border and within 120 units of us. Being potential-based, the bonus cannot be farmed by hovering, so it teaches the committed final approach on a pinned runner. A general approach term keeps the chaser honest. The defender keeps only the evade term, which has proven safe. The drill runs lighter (start 0.7, ends at 0.5) so most of the round is win/loss and match prep. Hparams and opponents stay unchanged because the club is improving and training is balanced (mirror attacker win rate 0.52).

Expected signal: Attacker wins vs bots-greedy rise from 52 to 65+ and vs Brave Pronghorn from 51 to 62+. Overall attacker win rate rises from about 0.82 to 0.86. Defender wins stay within about 4 points of 0.82, with Caiman and Pronghorn defender games roughly flat. Attacker time_to_tag stays at or below about 5.5 s. In training, the mirror attacker_win_rate rises slightly from 0.52 toward 0.6, and episode_len_mean falls from 358 to about 300. Elo rises 20-50 and widens the lead over bots-greedy. Drill checks should show card_auc above 0.65 and a cap-hit fraction near 0.

Diversity: With no charter, the club keeps its distinct identity of fast, open-field play in both roles (speeds 66/70 against league 51/35, very low corner time). This round adds a specialised wall-finishing attacker skill rather than imitating the border-hugging style common in the league.