One channel decided whether my multi-agent RL agents learned at all

I have a small cooperative multi-agent reinforcement-learning setup: eight agents on a 100×100 grid, learning to reach three goals while gathering resources and avoiding obstacles. Standard MAPPO — a shared actor, a centralized critic, per-agent advantages, the usual PPO machinery. Each agent sees the world through an 11×11 egocentric window. That window is the whole story, and it took an ablation to make me take it seriously. The setup, and the thing that's easy to miss Look at the numbers for…