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

[2608.14982] Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games? Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14982 (cs) [Submitted on 15 Aug 2026] Title: Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games? Authors: Wenji Fu View a PDF of the paper titled Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?, by Wenji Fu View PDF HTML (experimental) 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 games, and 7,200 fixed-seed games against three legacy opponents. Across matched Transformer backbones, HexRoPE reduces exact-belief posterior cross-entropy relative to no positional encoding by 0.278 on D6-transformed test orbits and 0.329 on a larger map; both hierarchical-bootstrap confidence intervals exclude zero, and both Holm-adjusted p-values are below 0.001. At 1k games, HexRoPE improves policy action accuracy by 4.63 percentage points over no encoding and 2.05 points over rectangular relative bias; the gains shrink to 1.55 and 0.41 points at 10k games. However, HexRoPE does not improve aggregate gameplay win rate: its paired effect over no encoding is -1.56 percentage points (95% CI [-4.50, 1.17]). Rectangular relative bias is strongest on D6 belief consistency but fails sharply when extrapolating from radius 3 to radius 4, while graph bias provides only a small blocked-edge gain. The results show that geometric inductive bias improves belief estimation and data-efficient imitation, but those representation gains do not automatically produce stronger closed-loop play. Comments: 7 pages, 4 figures, 3 tables Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML) Cite as: arXiv:2608.14982 [cs.LG] (or arXiv:2608.14982v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14982 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Wenji Fu [ view email ] [v1] Sat, 15 Aug 2026 02:20:10 UTC (42 KB) Full-text links: Access Paper: View a PDF of the paper titled Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?, by Wenji Fu View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI stat stat.ML References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?#610941
• LoST: A Location-to-Service Translation Protocol#420386
• Information as Structural Reduction of Future Possibility - A Formal Derivation from Restricted Transformability under Persistence Conditions#81362
• Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents#1155548
• A Comparative Study of Orthographic and Isometric Manual Drawing Methods on Accuracy in Object Reconstruction Among Architecture Students of National University – Mall of Asia.#299782