メニュー
Encode closed rectangular patrol routes as compact direction-distance strings for fleet pathfinding on toroidal game grids
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Memory-efficient Keras generator that streams sharded CSV files in chunks, renders strokes to images on-the-fly, and yields batches for training on datasets too large for memory
Stack 1D convolutions for local feature extraction before bidirectional LSTMs to classify variable-length stroke sequences into hundreds of doodle categories
Partition a large dataset into N balanced shards using integer key modulo arithmetic for reproducible, class-interleaved splits across CSV files
Normalize raw stroke coordinates to 0-255 range, resample at uniform arc-length spacing, then apply Ramer-Douglas-Peucker simplification
Render stroke sequences to grayscale images with temporal intensity encoding where earlier strokes are brighter and later strokes fade to encode drawing order
Score each face in a video as anomalous by computing L2 distance from the embedding centroid of all faces, then convert to probability via logistic function
| name | tabular-rectangular-flight-plan-encoding |
| description | Encode closed rectangular patrol routes as compact direction-distance strings for fleet pathfinding on toroidal game grids |
In grid-based game AI competitions, units follow flight plans encoded as strings of direction characters and distances (e.g., "N3E3S3W"). A rectangular route visits the perimeter of a box and returns to the origin, maximizing cells visited for resource collection. The plan length is constrained by unit count (floor(2 * ln(ships)) + 1), linking fleet size to patrol range.
from kaggle_environments.envs.kore_fleets.helpers import Direction
def build_rect_plan(start_dir_idx, side_length):
plan = ""
for i in range(4):
plan += Direction.from_index((start_dir_idx + i) % 4).to_char()
if i < 3:
plan += str(side_length)
return plan
# "N5E5S5W" — a 5x5 rectangle starting north, returns to origin
plan = build_rect_plan(0, 5)
# Minimum ships needed: exp((len(plan) - 1) / 2) ≈ 21 for a 9x9 box
floor(2 * ln(ships)) + 1 character limitln(ships)/20 per cell — many small fleets extract more than one large fleet