Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?

Excerpt

arXiv:2608.14982v1 Announce Type: cross Abstract: Transformers applied to spatial imperfect-information games must represent map geometry while tracking hidden entities through time. We ask whether geometry-aware positional encodings improve these capabilities, without claiming a new positional encoding. We construct a four-level benchmark on a hexagonal naval pursuit game: controlled geometry and topology probes, an exact-Bayes hidden-target tracking task, offline policy imitation at 1k and 10k