用对比学习提升时间推理能力，让模型仅靠自身表示就能解魔方。
Contrastive Representations for Temporal Reasoning
- 设计新负采样策略，消除误导性特征，增强时间结构感知
- 在魔方等复杂任务中，用更少搜索步数完成求解
- 首次实现仅靠学习表示即可解任意初始状态的魔方
在经典人工智能中，感知依赖于状态表示，而规划（可视为动作序列的时间推理）通常通过搜索实现。我们研究是否可通过同时捕捉感知与时间结构的表示来实现推理。发现主流的时间对比学习因依赖虚假特征，常无法有效捕获时间结构。为此提出组合式时间推理表示（CRTR），采用负采样机制可证明地消除这些虚假特征，促进时间推理。CRTR在具有复杂时间结构的任务如推箱子（Sokoban）和魔方（Rubik's Cube）上表现优异。尤其在魔方任务中，其学习到的表示能泛化至所有初始状态，并以比BestFS更少的搜索步骤求解，尽管解法更长。据我们所知，这是首个仅依赖学习表示、无需外部搜索算法即可高效解决任意魔方状态的方法。
原文摘要 · Abstract (English)
In classical AI, perception relies on learning state-based representations, while planning, which can be thought of as temporal reasoning over action sequences, is typically achieved through search. We study whether such reasoning can instead emerge from representations that capture both perceptual and temporal structure. We show that standard temporal contrastive learning, despite its popularity, often fails to capture temporal structure due to its reliance on spurious features. To address this, we introduce Combinatorial Representations for Temporal Reasoning (CRTR), a method that uses a negative sampling scheme to provably remove these spurious features and facilitate temporal reasoning. CRTR achieves strong results on domains with complex temporal structure, such as Sokoban and Rubik's Cube. In particular, for the Rubik's Cube, CRTR learns representations that generalize across all initial states and allow it to solve the puzzle using fewer search steps than BestFS, though with longer solutions. To our knowledge, this is the first method that efficiently solves arbitrary Cube states using only learned representations, without relying on an external search algorithm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。