2026.

Nervous Maze — Topology Contestability Study

A data-driven screening of ~1,000 candidate maze-tile topologies for Nervous Maze, a reinforcement-learning environment where the maze itself acts as an adversarial agent. Rather than trusting the A* navigator’s own test results as ground truth, I built an independent ranking method that separates genuine topology quality from evidence artifacts: a Wilson-corrected viability score (penalizing thin trial counts), two empirically non-redundant contestability signals (sustained route scarcity and response-level route disruption), and an explicit checkmate penalty. The result is a reproducible top-30 shortlist and a full evidence trail — comparison figures, a written scoring rationale, and cross-checks against hand-picked candidates — that fed directly into selecting the tile geometry for the project’s next RL training milestone.

Methods: statistical ranking under small-sample correction, redundancy analysis across candidate metrics, data visualization.