No-Regret Shannon Entropy Regularized Neural Contextual Bandit Online Learning for Robotic Grasping
Kyungjae Lee,Jaegu Choy,Yunho Choi,Hogun Kee,Songhwai Oh,Kyungjae Lee,Jaegu Choy,Yunho Choi,Hogun Kee,Songhwai Oh
In this paper, we propose a novel contextual bandit algorithm that employs a neural network as a reward estimator and utilizes Shannon entropy regularization to encourage exploration, which is called Shannon entropy regularized neural contextual bandits (SERN). In many learning-based algorithms for robotic grasping, the lack of the real-world data hampers the generalization performance of a model ...
