Evolving Collective Behaviors With Diverse But Predictable Sensor States

Payam Zahadat; Heiko Hamann; Thomas Schmickl

doi:10.7551/978-0-262-33027-5-ch036

Evolving Collective Behaviors With Diverse But Predictable Sensor States

Payam Zahadat
, Heiko Hamann
, Thomas Schmickl

Research output: Conference Article in Proceeding or Book/Report chapter › Conference abstract in proceedings › Research › peer-review

Abstract

Artificial evolution of collective behaviors can be implemented in different ways. Here, we extend the approach of Hamann (2014). The underlying concept is that the brain is permanently trying to predict future perceptions and a state of well-being is a state that allows for precise predictions (Friston, 2010). Striving for maximal prediction success needs to be complemented by a force that implements curiosity and exploration. In this abstract we present an extended method diverse-prediction that rewards not only for correct predictions but also for each visited sensory state.

Original language	English
Title of host publication	Proceedings of the European Conference on Artificial Life
Number of pages	1
Publisher	MIT Press
Publication date	1 Jul 2015
Pages	174
DOIs	https://doi.org/10.7551/978-0-262-33027-5-ch036
Publication status	Published - 1 Jul 2015
Externally published	Yes
Event	European Conference on Artificial Life - York, United Kingdom Duration: 20 Jul 2015 → 24 Jul 2015 Conference number: 13

Conference

Conference	European Conference on Artificial Life
Number	13
Country/Territory	United Kingdom
City	York
Period	20/07/2015 → 24/07/2015

Keywords

artificial evolution
collective behavior
predictive processing
active inference
diverse-prediction

Access to Document

10.7551/978-0-262-33027-5-ch036Licence: CC BY

Cite this

@inbook{639c359c6c4b4358b55df41747f59b38,

title = "Evolving Collective Behaviors With Diverse But Predictable Sensor States",

abstract = "Artificial evolution of collective behaviors can be implemented in different ways. Here, we extend the approach of Hamann (2014). The underlying concept is that the brain is permanently trying to predict future perceptions and a state of well-being is a state that allows for precise predictions (Friston, 2010). Striving for maximal prediction success needs to be complemented by a force that implements curiosity and exploration. In this abstract we present an extended method diverse-prediction that rewards not only for correct predictions but also for each visited sensory state.",

keywords = "artificial evolution, collective behavior, predictive processing, active inference, diverse-prediction",

author = "Payam Zahadat and Heiko Hamann and Thomas Schmickl",

year = "2015",

month = jul,

day = "1",

doi = "10.7551/978-0-262-33027-5-ch036",

language = "English",

pages = "174",

booktitle = "Proceedings of the European Conference on Artificial Life",

publisher = "MIT Press",

address = "United States",

note = "European Conference on Artificial Life<br/>, ECAL 2015 ; Conference date: 20-07-2015 Through 24-07-2015",

}

TY - ABST

T1 - Evolving Collective Behaviors With Diverse But Predictable Sensor States

AU - Zahadat, Payam

AU - Hamann, Heiko

AU - Schmickl, Thomas

N1 - Conference code: 13

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Artificial evolution of collective behaviors can be implemented in different ways. Here, we extend the approach of Hamann (2014). The underlying concept is that the brain is permanently trying to predict future perceptions and a state of well-being is a state that allows for precise predictions (Friston, 2010). Striving for maximal prediction success needs to be complemented by a force that implements curiosity and exploration. In this abstract we present an extended method diverse-prediction that rewards not only for correct predictions but also for each visited sensory state.

AB - Artificial evolution of collective behaviors can be implemented in different ways. Here, we extend the approach of Hamann (2014). The underlying concept is that the brain is permanently trying to predict future perceptions and a state of well-being is a state that allows for precise predictions (Friston, 2010). Striving for maximal prediction success needs to be complemented by a force that implements curiosity and exploration. In this abstract we present an extended method diverse-prediction that rewards not only for correct predictions but also for each visited sensory state.

KW - artificial evolution

KW - collective behavior

KW - predictive processing

KW - active inference

KW - diverse-prediction

U2 - 10.7551/978-0-262-33027-5-ch036

DO - 10.7551/978-0-262-33027-5-ch036

M3 - Conference abstract in proceedings

SP - 174

BT - Proceedings of the European Conference on Artificial Life

PB - MIT Press

T2 - European Conference on Artificial Life<br/>

Y2 - 20 July 2015 through 24 July 2015

ER -

Evolving Collective Behaviors With Diverse But Predictable Sensor States

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this