An initial attempt of combining visual selective attention with deep reinforcement learning

Autor:	Yuezhang, Liu, Zhang, Ruohan, Ballard, Dana H.
Rok vydání:	2018
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Visual attention serves as a means of feature selection mechanism in the perceptual system. Motivated by Broadbent's leaky filter model of selective attention, we evaluate how such mechanism could be implemented and affect the learning process of deep reinforcement learning. We visualize and analyze the feature maps of DQN on a toy problem Catch, and propose an approach to combine visual selective attention with deep reinforcement learning. We experiment with optical flow-based attention and A2C on Atari games. Experiment results show that visual selective attention could lead to improvements in terms of sample efficiency on tested games. An intriguing relation between attention and batch normalization is also discovered. Comment: 7 pages, 8 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1811.04407 Zobrazit plný text záznamu View this record from Arxiv