幾何と時間を活用したマルチタスクロボット学習における分布外タスクへの高速適応
Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning
ロボットタスクの物理的構造の共有に着目し、事前学習済みポリシーをブラックボックス事前分布として再利用することで、少量のオフラインデータから分布外の新規タスクへ適応する手法を検討した論文。
著者: K. R. Zentner, Ryan Julian, Ujjwal Puri, Yulun Zhang, Gaurav Sukhatme
分類: cs.RO, cs.AI
原文アブストラクト
We explore possible methods for multi-task transfer learning which seek to exploit the shared physical structure of robotics tasks. Specifically, we train policies for a base set of pre-training tasks, then experiment with adapting to new off-distribution tasks, using simple architectural approaches for re-using these policies as black-box priors. These approaches include learning an alignment of either the observation space or action space from a base to a target task to exploit rigid body structure, and methods for learning a time-domain switching policy across base tasks which solves the target task, to exploit temporal coherence. We find that combining low-complexity target policy classes, base policies as black-box priors, and simple optimization algorithms allows us to acquire new tasks outside the base task distribution, using small amounts of offline training data.
