菜单
Divide a game into repeating phases (attack, mine, spawn) with turn-modular gating so the agent cycles between aggressive and economic behavior
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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-phase-based-strategy-cycling |
| description | Divide a game into repeating phases (attack, mine, spawn) with turn-modular gating so the agent cycles between aggressive and economic behavior |
In multi-phase game AI, a single static strategy loses to adaptive play. Dividing the game into repeating cycles — e.g., attack (turns 0-20), mine (20-90), idle/spawn (90-100) within each 100-turn block — lets a heuristic agent alternate between aggression and economy. Each phase has different action priorities and ship allocation rules.
def agent(obs, config):
board = Board(obs, config)
me = board.current_player
turn = board.step
cycle_pos = turn % 100
for shipyard in me.shipyards:
if cycle_pos < 20 and shipyard.ship_count >= 50:
launch_attack(shipyard, board)
elif 20 <= cycle_pos < 90 and shipyard.ship_count >= 10 and turn % 7 == 0:
launch_mining_fleet(shipyard, turn)
elif me.kore >= board.configuration.spawn_cost * shipyard.max_spawn:
shipyard.next_action = ShipyardAction.spawn_ships(shipyard.max_spawn)
return me.next_actions