Learning to Order: Task Sequencing as In-Context Optimization
This addresses a core open problem in domains like robotics and autonomous driving, though it appears incremental as it builds on prior meta-learning approaches.
The paper tackles the problem of task sequencing in deep learning by meta-learning a transformer-based architecture over synthetically generated sequencing problems, achieving few-shot generalization and discovering optimal sequences significantly quicker than baselines.
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.