标题:A self-organizing developmental cognitive architecture with interactive reinforcement learning
作者:Huang, Ke; Ma, Xin; Song, Rui; Rong, Xuewen; Tian, Xincheng; Li, Yibin
作者机构:[Huang, Ke; Ma, Xin; Song, Rui; Rong, Xuewen; Tian, Xincheng; Li, Yibin] Shandong Univ, Sch Control Sci & Engn, Ctr Robot, Jinan, Shandong, Peoples R 更多
通讯作者:Ma, Xin;Ma, X
通讯作者地址:[Ma, X]Shandong Univ, Sch Control Sci & Engn, Ctr Robot, Jinan, Shandong, Peoples R China.
来源:NEUROCOMPUTING
出版年:2020
卷:377
页码:269-285
DOI:10.1016/j.neucom.2019.07.109
关键词:Cognitive development; Online learning; Self-organizing neural network;; Object recognition; Interactive reinforcement learning
摘要:Developmental cognitive systems can endow robots with the abilities to incrementally learn knowledge and autonomously adapt to complex environments. Conventional cognitive methods often acquire knowledge through passive perception, such as observing and listening. However, this learning way may generate incorrect representations inevitably and cannot correct them online without any feedback. To tackle this problem, we propose a biologically-inspired hierarchical cognitive system called Self-Organizing Developmental Cognitive Architecture with Interactive Reinforcement Learning (SODCA-IRL). The architecture introduces interactive reinforcement learning into hierarchical self-organizing incremental neural networks to simultaneously learn object concepts and fine-tune the learned knowledge by interacting with humans. In order to realize the integration, we equip individual neural networks with a memory model, which is designed as an exponential function controlled by two forgetting factors to simulate the consolidation and forgetting processes of humans. Besides, an interactive reinforcement strategy is designed to provide appropriate rewards and execute mistake correction. The feedback acts on the forgetting factors to reinforce or weaken the memory of neurons. Therefore, correct knowledge is preserved while incorrect representations are forgotten. Experimental results show that the proposed method can make effective use of the feedback from humans to improve the learning effectiveness significantly and reduce the model redundancy. (c) 2019 Elsevier B.V. All rights reserved.
收录类别:EI;SCIE;SSCI
资源类型:期刊论文
TOP