Information-theoretic Cost of Decision-making in Joint Action

Dari Trendafilov, Daniel Polani, Alois Ferscha

2021

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.

Paper Citation

in Harvard Style

Trendafilov D., Polani D. and Ferscha A. (2021). Information-theoretic Cost of Decision-making in Joint Action.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-484-8, pages 304-311. DOI: 10.5220/0010252303040311

in Bibtex Style

@conference{icaart21,
author={Dari Trendafilov and Daniel Polani and Alois Ferscha},
title={Information-theoretic Cost of Decision-making in Joint Action},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2021},
pages={304-311},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010252303040311},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Information-theoretic Cost of Decision-making in Joint Action
SN - 978-989-758-484-8
AU - Trendafilov D.
AU - Polani D.
AU - Ferscha A.
PY - 2021
SP - 304
EP - 311
DO - 10.5220/0010252303040311