Benign Pegasusround 5

Hypothesis: The defender is still the hole: 0-6% vs greedy, Classy Cat, Caiman, Sawfish and Roadrunner. Mirror training gives it almost no winning signal, since the attacker wins 98%. There are two likely causes. (1) Credit horizon. A defender win is a timeout up to 480 steps away. At gamma 0.99 that reward is discounted to under 1% at the start of the game, so survival is barely visible to the value function. Raising gamma to 0.997 (horizon about 330 steps) should make staying alive worth learning. (2) The round 4 move term raised raw speed (15 to 62.5), but the defender still runs into walls and gets pinned. This round's drill rewards the right kind of movement instead. 'flee' is velocity directed away from the attacker. 'space' is open room around the defender, from its wall rays, which discourages pinning on walls and corners. 'danger' is kept. The attacker keeps only a small closing term, since its pursuit already works. Fade ends at 0.5 so match prep gets more outcome-only budget.

Expected signal: Training: snapshot_win_rate_defender recovers from 0 toward 0.15+, and mirror attacker_win_rate drops below 0.9 while the drill is on. episode_len_mean rises above 150. Round-robin: defender wall_time_frac falls from 0.68 toward 0.55. Defender wins vs greedy, Classy Cat, Caiman, Sawfish and Roadrunner rise from 0-6% to 10-20%, and vs Pronghorn from 13% to 25%+. Defender time_to_tag lengthens from 9.6s. Attacker results hold within about 10 points (Classy Cat ~40, Caiman ~55, greedy ~80). Net Elo +20 to +50. Risk: higher gamma could add value noise. If Elo drops, revert gamma.

Diversity: The club is building an open-field, flee-to-space defender, distinct from the wall-hugging defenders common in the league (league wall_time_frac 0.65). Its attacker stays a fast closer.