Learning Sparse and Meaningful Representations Through Embodiment

02/23/2021
by   Viviane Clay, et al.
1

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.

READ FULL TEXT

page 9

page 10

page 11

page 12

page 13

page 15

page 16

page 17

research
02/03/2021

Fast Concept Mapping: The Emergence of Human Abilities in Artificial Neural Networks when Learning Embodied and Self-Supervised

Most artificial neural networks used for object detection and recognitio...
research
12/03/2021

Divergent representations of ethological visual inputs emerge from supervised, unsupervised, and reinforcement learning

Artificial neural systems trained using reinforcement, supervised, and u...
research
01/21/2020

Unsupervisedly Learned Representations: Should the Quest be Over?

There exists a Classification accuracy gap of about 20 methods of genera...
research
12/09/2019

Learning Sparse Representations Incrementally in Deep Reinforcement Learning

Sparse representations have been shown to be useful in deep reinforcemen...
research
06/27/2019

Emergence of Exploratory Look-Around Behaviors through Active Observation Completion

Standard computer vision systems assume access to intelligently captured...
research
09/23/2019

Where to Look Next: Unsupervised Active Visual Exploration on 360° Input

We address the problem of active visual exploration of large 360 inputs....
research
12/14/2022

Learning and Predicting Multimodal Vehicle Action Distributions in a Unified Probabilistic Model Without Labels

We present a unified probabilistic model that learns a representative se...

Please sign up or login with your details

Forgot password? Click here to reset