让AI学会快速排序任务，少样本下表现远超传统方法。
Learning to Order: Task Sequencing as In-Context Optimization
- 用Transformer在合成任务路径上元学习排序策略
- 少样本下发现最优序列速度比基线快数倍
- 适合机器人、自动驾驶等需动态调度的场景
任务排序（TS）是深度学习中的核心开放问题，广泛存在于机器人装配线、自动驾驶等领域。以往方法难以在仅有少量示范的情况下泛化到新任务。本文表明，深度神经网络可在无限数量的合成任务中进行元学习，实现少样本泛化。我们基于变换器架构，在由有向图路径生成的序列轨迹数据集上进行训练。大规模实验证明，元学习模型发现最优任务序列的速度显著快于非元学习基线。
原文摘要 · Abstract (English)
Task sequencing (TS) is one of the core open problems in Deep Learning, arising in a plethora of real-world domains, from robotic assembly lines to autonomous driving. Unfortunately, prior work has not convincingly demonstrated the generalization ability of meta-learned TS methods to solve new TS problems, given few initial demonstrations. In this paper, we demonstrate that deep neural networks can meta-learn over an infinite prior of synthetically generated TS problems and achieve a few-shot generalization. We meta-learn a transformer-based architecture over datasets of sequencing trajectories generated from a prior distribution that samples sequencing problems as paths in directed graphs. In a large-scale experiment, we provide ample empirical evidence that our meta-learned models discover optimal task sequences significantly quicker than non-meta-learned baselines.
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。