跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 14 天前AI 評分37

World model 要用多少次觀察,才能在測試時學會未見過的遊戲機制?

How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time

AI 導讀

WARC 是一個有 35M 參數、以其他遊戲預訓練的 vision transformer,研究其在測試時透過有限互動學習新遊戲機制的能力。在未見遊戲中,WARC 有五分之四的機制能以至少 80% 準確率預測受影響格子;其中一半約經 80 次觀察便達到此準確率。.closed-loop 遊玩公開遊戲時,WARC-Agent 將探索器的官方效率分數由 0.15 提升至 0.46。

正文

Published on Nov 9

Authors:

,

,

Abstract

World models enable agents to plan and learn from imagined experience, but in an unfamiliar environment they must learn its mechanics from limited interaction. A mechanic is a rule for how an action or an interaction changes part of the environment. Each occurrence of a mechanic that the model observes is one exposure. We ask how many exposures a world model needs to predict the effects of a new environment's mechanics. We address this question on ARC-AGI-3, a benchmark of interactive games defined by their programs. We introduce MechEval, which labels 69 recurring mechanics across 20 games from these programs. It scores each prediction on the cells the mechanic changes at each exposure. As a test bed, we build WARC (World model for ARC-AGI-3), a 35M-parameter vision transformer that is pretrained on other games and updates all of its parameters after each transition. On held-out games, WARC learns to predict four in five mechanics with at least 80% accuracy on the cells they change and keeps that accuracy to the end of the recordings. Half of them reach that accuracy within about 80 exposures, in a single play of the game, and without updates only one in seven does at all. In closed-loop play on the public games, WARC-Agent, which pairs WARC with a fixed graph explorer, triples the explorer's official efficiency score from 0.15 to 0.46, mostly through test-time training. On the hidden games of the Kaggle leaderboard, our entry scores 0.20.

View arXiv page View PDF GitHub 0 Add to collection

Get this paper in your agent:

hf papers read 2611.12324

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.12324 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.12324 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.12324 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co