Learning sparse and meaningful representations through embodiment

Viviane Clay; Peter König; Kai-Uwe Kühnberger; Gordon Pipa

doi:10.1016/j.neunet.2020.11.004

Learning sparse and meaningful representations through embodiment

Standard

Learning sparse and meaningful representations through embodiment. / Clay, Viviane; König, Peter; Kühnberger, Kai-Uwe; Pipa, Gordon.

in: NEURAL NETWORKS, Jahrgang 134, 02.2021, S. 23-41.

Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung

Harvard

Clay, V, König, P, Kühnberger, K-U & Pipa, G 2021, 'Learning sparse and meaningful representations through embodiment', NEURAL NETWORKS, Jg. 134, S. 23-41. https://doi.org/10.1016/j.neunet.2020.11.004

APA

Clay, V., König, P., Kühnberger, K-U., & Pipa, G. (2021). Learning sparse and meaningful representations through embodiment. NEURAL NETWORKS, 134, 23-41. https://doi.org/10.1016/j.neunet.2020.11.004

Vancouver

Clay V, König P, Kühnberger K-U, Pipa G. Learning sparse and meaningful representations through embodiment. NEURAL NETWORKS. 2021 Feb;134:23-41. https://doi.org/10.1016/j.neunet.2020.11.004

Bibtex

@article{60204554f3a8421ca424241914fc14f1,

title = "Learning sparse and meaningful representations through embodiment",

abstract = "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.",

author = "Viviane Clay and Peter K{\"o}nig and Kai-Uwe K{\"u}hnberger and Gordon Pipa",

year = "2021",

month = feb,

doi = "10.1016/j.neunet.2020.11.004",

language = "English",

volume = "134",

pages = "23--41",

journal = "NEURAL NETWORKS",

issn = "0893-6080",

publisher = "Elsevier Limited",

}

RIS

TY - JOUR

T1 - Learning sparse and meaningful representations through embodiment

AU - Clay, Viviane

AU - König, Peter

AU - Kühnberger, Kai-Uwe

AU - Pipa, Gordon

PY - 2021/2

Y1 - 2021/2

N2 - 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.

AB - 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.

U2 - 10.1016/j.neunet.2020.11.004

DO - 10.1016/j.neunet.2020.11.004

M3 - SCORING: Journal article

C2 - 33279863

VL - 134

SP - 23

EP - 41

JO - NEURAL NETWORKS

JF - NEURAL NETWORKS

SN - 0893-6080

ER -