← 研踪 PaperTrailarXiv:2606.20967 · v2
Formalizing and Estimating Task-Space Complexity for Zero-shot Generalization
首次提交 2026-06-19 06:07
版本更新 2026-10-27 01:52
雷达观测 2026-10-29 00:35
摘要
Generalization is crucial for modern control, but learning across tasks can be costly. Recent work shows that zero-shot transfer, in which a controller designed for a source task is directly deployed to a target task, can achieve strong performance. We formalize task-space complexity, which characterizes the difficulty of achieving sufficiently good performance across a collection of tasks, by casting source selection as a covering problem. We provide bounds on the complexity and demonstrate its applicability.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-10-27 01:52 · 最新观测版本
Formalizing and Estimating Task-Space Complexity for Zero-shot Generalization
Generalization is crucial for modern control, but learning across tasks can be costly. Recent work shows that zero-shot transfer, in which a controller designed for a source task is directly deployed to a target task, can achieve strong performance. We formalize task-space complexity, which characterizes the difficulty of achieving sufficiently good performance across a collection of tasks, by casting source selection as a covering problem. We provide bounds on the complexity and demonstrate its applicability.
查看此版本解读 →查看此版本原文 ↗