Exploration and exploitation in visuomotor prediction of autonomous agents

Laurens Bliek

Exploration and exploitation in visuomotor prediction of autonomous agents

Laurens Bliek

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and tested in a simple system: a camera moving over a 2D greyscale image.

Original language	English
Title of host publication	Proceedings of BNAIC 2013: 25th Belgium-Netherlands Conference on Artificial Intelligence
Pages	1-8
Number of pages	8
Publication status	Published - 2013
Externally published	Yes
Event	25th Benelux Conference on Artificial Intelligence (BNAIC2013) - Delft, Netherlands Duration: 7 Nov 2013 → 8 Nov 2013 Conference number: 25

Conference

Conference	25th Benelux Conference on Artificial Intelligence (BNAIC2013)
Abbreviated title	BNAIC 2013
Country/Territory	Netherlands
City	Delft
Period	7/11/13 → 8/11/13

Cite this

@inproceedings{f0a65eea9e4b49e4b074e0c81ac232d5,

title = "Exploration and exploitation in visuomotor prediction of autonomous agents",

abstract = "This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and tested in a simple system: a camera moving over a 2D greyscale image.",

author = "Laurens Bliek",

year = "2013",

language = "English",

pages = "1--8",

booktitle = "Proceedings of BNAIC 2013: 25th Belgium-Netherlands Conference on Artificial Intelligence",

note = "25th Benelux Conference on Artificial Intelligence (BNAIC2013), BNAIC 2013 ; Conference date: 07-11-2013 Through 08-11-2013",

}

TY - GEN

T1 - Exploration and exploitation in visuomotor prediction of autonomous agents

AU - Bliek, Laurens

N1 - Conference code: 25

PY - 2013

Y1 - 2013

N2 - This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and tested in a simple system: a camera moving over a 2D greyscale image.

AB - This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and tested in a simple system: a camera moving over a 2D greyscale image.

UR - https://www.scopus.com/pages/publications/85072681320

M3 - Conference contribution

AN - SCOPUS:85072681320

SP - 1

EP - 8

BT - Proceedings of BNAIC 2013: 25th Belgium-Netherlands Conference on Artificial Intelligence

T2 - 25th Benelux Conference on Artificial Intelligence (BNAIC2013)

Y2 - 7 November 2013 through 8 November 2013

ER -

Exploration and exploitation in visuomotor prediction of autonomous agents

Abstract

Conference

Other files and links

Fingerprint

Cite this