Information-theoretic cost of decision-making in joint action

Dari Trendafilov; Daniel Polani; Alois Ferscha

doi:10.5220/0010252303040311

Information-theoretic cost of decision-making in joint action

Dari Trendafilov, Daniel Polani, Alois Ferscha

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We investigate the information processing cost relative to utility, associated with joint action in dyadic decision-making. Our approach, built on the Relevant Information formalism, combines Shannon's Information Theory and Markov Decision Processes for modelling dyadic interaction, where two agents with independent controllers move an object together with fully redundant control in a grid world. Results show that increasing collaboration relaxes the pressure on required information intake and vice versa, antagonistic behavior takes a higher toll on information bandwidth. In this trade-off the particular embodiment of the environment plays a key role, demonstrated in simulations with informationally parsimonious optimal controllers.

Original language	English
Title of host publication	ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence
Editors	Ana Paula Rocha, Luc Steels, Jaap van den Herik
Publisher	SciTePress
Pages	304-311
Number of pages	8
Volume	1
ISBN (Electronic)	9789897584848
DOIs	https://doi.org/10.5220/0010252303040311
Publication status	Published - 6 Feb 2021
Event	13th International Conference on Agents and Artificial Intelligence, ICAART 2021 - Virtual, Online Duration: 4 Feb 2021 → 6 Feb 2021 Conference number: 13 https://icaart.scitevents.org/?y=2021

Publication series

Name	ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence
Publisher	Scitepress
Volume	1
ISSN (Print)	2184-433X

Conference

Conference	13th International Conference on Agents and Artificial Intelligence, ICAART 2021
Abbreviated title	ICAART 2021
City	Virtual, Online
Period	4/02/21 → 6/02/21
Internet address	https://icaart.scitevents.org/?y=2021

Keywords

Collective behavior
Complex systems
Information dynamics
Information theory

Access to Document

10.5220/0010252303040311Licence: CC BY-NC-ND

Cite this

Trendafilov, D., Polani, D., & Ferscha, A. (2021). Information-theoretic cost of decision-making in joint action. In A. P. Rocha, L. Steels, & J. van den Herik (Eds.), ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence (Vol. 1, pp. 304-311). (ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence; Vol. 1). SciTePress. https://doi.org/10.5220/0010252303040311

Trendafilov, Dari ; Polani, Daniel ; Ferscha, Alois. / Information-theoretic cost of decision-making in joint action. ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence. editor / Ana Paula Rocha ; Luc Steels ; Jaap van den Herik. Vol. 1 SciTePress, 2021. pp. 304-311 (ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence).

@inproceedings{28a81efed5f84055869b10a434d717e9,

title = "Information-theoretic cost of decision-making in joint action",

abstract = "We investigate the information processing cost relative to utility, associated with joint action in dyadic decision-making. Our approach, built on the Relevant Information formalism, combines Shannon's Information Theory and Markov Decision Processes for modelling dyadic interaction, where two agents with independent controllers move an object together with fully redundant control in a grid world. Results show that increasing collaboration relaxes the pressure on required information intake and vice versa, antagonistic behavior takes a higher toll on information bandwidth. In this trade-off the particular embodiment of the environment plays a key role, demonstrated in simulations with informationally parsimonious optimal controllers.",

keywords = "Collective behavior, Complex systems, Information dynamics, Information theory",

author = "Dari Trendafilov and Daniel Polani and Alois Ferscha",

note = "{\textcopyright} 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved; 13th International Conference on Agents and Artificial Intelligence, ICAART 2021, ICAART 2021 ; Conference date: 04-02-2021 Through 06-02-2021",

year = "2021",

month = feb,

day = "6",

doi = "10.5220/0010252303040311",

language = "English",

volume = "1",

series = "ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence",

publisher = "SciTePress",

pages = "304--311",

editor = "Rocha, {Ana Paula} and Luc Steels and {van den Herik}, Jaap",

booktitle = "ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence",

url = "https://icaart.scitevents.org/?y=2021",

}

Trendafilov, D, Polani, D & Ferscha, A 2021, Information-theoretic cost of decision-making in joint action. in AP Rocha, L Steels & J van den Herik (eds), ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence. vol. 1, ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence, vol. 1, SciTePress, pp. 304-311, 13th International Conference on Agents and Artificial Intelligence, ICAART 2021, Virtual, Online, 4/02/21. https://doi.org/10.5220/0010252303040311

Information-theoretic cost of decision-making in joint action. / Trendafilov, Dari; Polani, Daniel; Ferscha, Alois.
ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence. ed. / Ana Paula Rocha; Luc Steels; Jaap van den Herik. Vol. 1 SciTePress, 2021. p. 304-311 (ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Information-theoretic cost of decision-making in joint action

AU - Trendafilov, Dari

AU - Polani, Daniel

AU - Ferscha, Alois

N1 - Conference code: 13

PY - 2021/2/6

Y1 - 2021/2/6

N2 - We investigate the information processing cost relative to utility, associated with joint action in dyadic decision-making. Our approach, built on the Relevant Information formalism, combines Shannon's Information Theory and Markov Decision Processes for modelling dyadic interaction, where two agents with independent controllers move an object together with fully redundant control in a grid world. Results show that increasing collaboration relaxes the pressure on required information intake and vice versa, antagonistic behavior takes a higher toll on information bandwidth. In this trade-off the particular embodiment of the environment plays a key role, demonstrated in simulations with informationally parsimonious optimal controllers.

AB - We investigate the information processing cost relative to utility, associated with joint action in dyadic decision-making. Our approach, built on the Relevant Information formalism, combines Shannon's Information Theory and Markov Decision Processes for modelling dyadic interaction, where two agents with independent controllers move an object together with fully redundant control in a grid world. Results show that increasing collaboration relaxes the pressure on required information intake and vice versa, antagonistic behavior takes a higher toll on information bandwidth. In this trade-off the particular embodiment of the environment plays a key role, demonstrated in simulations with informationally parsimonious optimal controllers.

KW - Collective behavior

KW - Complex systems

KW - Information dynamics

KW - Information theory

UR - http://www.scopus.com/inward/record.url?scp=85103839138&partnerID=8YFLogxK

U2 - 10.5220/0010252303040311

DO - 10.5220/0010252303040311

M3 - Conference contribution

AN - SCOPUS:85103839138

VL - 1

T3 - ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence

SP - 304

EP - 311

BT - ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence

A2 - Rocha, Ana Paula

A2 - Steels, Luc

A2 - van den Herik, Jaap

PB - SciTePress

T2 - 13th International Conference on Agents and Artificial Intelligence, ICAART 2021

Y2 - 4 February 2021 through 6 February 2021

ER -

Trendafilov D, Polani D, Ferscha A. Information-theoretic cost of decision-making in joint action. In Rocha AP, Steels L, van den Herik J, editors, ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence. Vol. 1. SciTePress. 2021. p. 304-311. (ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence). doi: 10.5220/0010252303040311

Information-theoretic cost of decision-making in joint action

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this