Yuxi HAN, Dequan LI, Yang YANG. Significance extraction based on data augmentation for reinforcement learning[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2400406
@article{title="Significance extraction based on data augmentation for reinforcement learning", author="Yuxi HAN, Dequan LI, Yang YANG", journal="Frontiers of Information Technology & Electronic Engineering", year="in press", publisher="Zhejiang University Press & Springer", doi="https://doi.org/10.1631/FITEE.2400406" }
%0 Journal Article %T Significance extraction based on data augmentation for reinforcement learning %A Yuxi HAN %A Dequan LI %A Yang YANG %J Frontiers of Information Technology & Electronic Engineering %P %@ 2095-9184 %D in press %I Zhejiang University Press & Springer doi="https://doi.org/10.1631/FITEE.2400406"
TY - JOUR T1 - Significance extraction based on data augmentation for reinforcement learning A1 - Yuxi HAN A1 - Dequan LI A1 - Yang YANG J0 - Frontiers of Information Technology & Electronic Engineering SP - EP - %@ 2095-9184 Y1 - in press PB - Zhejiang University Press & Springer ER - doi="https://doi.org/10.1631/FITEE.2400406"
Abstract: Deep reinforcement learning has shown remarkable capabilities in visual tasks, but it does not have a good generalization ability in the context of interference signals in the input images; this approach is therefore hard to be applied to trained agents in a new environment. To enable agents to distinguish between noise signals and important pixels in images, data augmentation techniques and the establishment of auxiliary networks are proven effective solutions. We introduce a novel algorithm, namely, Saliency-extracted Q-value by augmentation (SEQA), which encourages the agent to explore unknown states more comprehensively and focus its attention on important information. Specifically, SEQA masks out interfering features and extracts salient features and then updates the mask decoder network with critic losses to encourage the agent to focus on important features and make correct decisions. We evaluate our algorithm on the DeepMind Control generalization benchmark, and the experimental results show that our algorithm greatly improves training efficiency and stability. Meanwhile, our algorithm is either superior or equal to the state-of-the-art reinforcement learning methods in terms of sample efficiency and generalization.
Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article
Reference
Open peer comments: Debate/Discuss/Question/Opinion
Open peer comments: Debate/Discuss/Question/Opinion
<1>