Benign Pegasusround 7

Hypothesis: The defender gains from rounds 5-6 are in place: 88 vs greedy, 85+ vs Roadrunner and Magpie, corner time 0.02 and time_to_tag 13.6s. The attacker regressed in the same round: 12/100 vs greedy (37 before) and 38 vs Classy Cat (about 80 expected). Mirror attacker_win_rate fell to 0.55 because the defender now outpaces the attacker. The drill's only attacker term, the per-step closing delta, is satisfied by hovering near the defender. The attacker's high direction-change rate (4.73 against a league 2.8) and the stalls against corner-parked greedy defenders fit that. This round keeps the defender terms (flee, space, danger) unchanged so the evasion habit holds, and strengthens the attacker side. 'chase' goes from 0.001 to 0.0015. A new persistent 'press' term penalises distance to the defender, doubled when the defender sits within 30 units of a wall or corner (its position is inferred from x+opp_dx and y+opp_dy). Waiting near a parked defender then costs reward every step, and committing to the tag is the only way out. Hparams and opponents are unchanged, since gamma 0.997 has produced two good rounds.

Expected signal: Round-robin: attacker vs greedy rises from 12 to 25+, vs Classy Cat from 38 to 45+, vs Caiman from 35 to 40+. Attacker direction_changes_per_sec falls toward 3.5. Attacker vs mid clubs holds at 70+. Defender results hold within about 5 points (greedy ~85, Roadrunner and Magpie ~85, Cat 10-15, Caiman ~20). Training: mirror attacker_win_rate rises from 0.55 toward 0.65-0.75 while the drill is on, and episode_len_mean drops somewhat from 336. Net Elo +15 to +35. If the defender results drop sharply instead, the press weight was too high: reduce it next round.

Diversity: Benign Pegasus keeps its identity as a fast, roaming evader (defender speed 80 against a league 55, almost no corner time) and adds a committed, corner-pressing attacker rather than copying the league's wall-parking style.