Meta-Learning Hypothesis Spaces for Sequential Decision-making. (arXiv:2202.00602v3 [stat.ML] UPDATED)

Web: http://arxiv.org/abs/2202.00602

Obtaining reliable, adaptive confidence sets for prediction functions
(hypotheses) is a central challenge in sequential decision-making tasks, such
as bandits and model-based reinforcement learning. These confidence sets
typically rely on prior assumptions on the hypothesis space, e.g., the known
kernel of a Reproducing Kernel Hilbert Space (RKHS). Hand-designing such
kernels is error prone, and misspecification may lead to poor or unsafe
performance. In this work, we propose to meta-learn a kernel from offline data
(Meta-KeL). For the case where the …

arxiv decision hypothesis learning making meta meta-learning ml