.png){kind=icon}
返回
Learning sparse and meaningful representations through embodiment
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2020.11.004.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
How do humans acquire a meaningful understanding of the world with little to no supervision or semantic labels provided by the environment? Here we investigate embodiment with a closed loop between action and perception as one key component in this process. We take a close look at the representations learned by a deep reinforcement learning agent that is trained with high-dimensional visual observations collected in a 3D environment with very sparse rewards. We show that this agent learns stable representations of meaningful concepts such as doors without receiving any semantic labels. Our results show that the agent learns to represent the action relevant information, extracted from a simulated camera stream, in a wide variety of sparse activation patterns. The quality of the representations learned shows the strength of embodied learning and its advantages over fully supervised approaches. (C) 2020 The Authors. Published by Elsevier Ltd.
Keyword:
Reinforcement learning
Deep learning
Embodiment
Embodied cognition
Representation learning
Sparse coding
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
PURIFIED ANTIGEN RADIOIMMUNOASSAY IN SEROLOGICAL DIAGNOSIS OF SCHISTOSOMIASIS MANSONI.png)
The Lancet
The LancetIF0
PREAI
分享收藏Energetics of cooperative protein-DNA interactions: comparison between quantitative deoxyribonuclease footprint titration and filter bindingBiochemistry
BiochemistryIF0
PREAI
分享收藏分享收藏
查看更多内容