Exhaustive exploration strategies for NPCS in game maps
Bibliographic record
Abstract
Much work has been done on automated terrain mapping in the field of robotics.And while there has been interest in Artificial Intelligence (AI) navigation in video games, there currently exists no formalized approach by which a non-player character (NPC) can automatically explore and map out an entire game level.In this dissertation, we present a method that generates an exploratory path in the game map, using which an NPC will be able to uncover all parts of the map.Our problem statement resembles that of the Watchman Route Problem, studied theoretically in computational geometry.We model a game map as a 2-dimensional polygon with holes, then using the Art Gallery Theorem compute a set of camera points that collectively guarantee full coverage of the map, and connect these cameras using motion planning graphs called roadmaps.From there we use visibility polygons, polygon merging and shortest-path calculations, to develop five different strategies for tours that visit the cameras.We identify factors that influence the performance of these strategies, and experimentally analyse their influence using metrics we have developed.Additionally, we compare the performances of the strategies themselves, as well as test on different types of roadmaps.Our experiments are carried out on large and complex maps from commercial games.We have devised a simple procedure for the collection and conversion of such maps to an easily readable format.The strategies proposed can be used by both hostile and non-hostile NPCs in different spatial search scenarios.For example, to locate a player, or to help a player uncover a map in fog-of-war settings.We hope our efforts will encourage further work on this relatively nascent topic.The development of more complex metrics, and more human-like strategies, could help quantify the "explorability" of a map, and aid in level design decisions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".