Interactive Inference: A Multi-Agent Model of Cooperative Joint Actions
IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2024-02 · 54 (2) · 704-715
DOI: 10.1109/tsmc.2023.3312585 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2024-02. Verfasst von Domenico Maisto und 2 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: MUR–PRIN2020, EU Horizon 2020 Framework Programme for Research and Innovation through Human Brain Project SGA3 under the Specific, TAILOR.
Abstract (Originalsprache)
We advance a novel computational model of multi-agent, cooperative joint actions that is grounded in the cognitive framework of active inference. The model assumes that to solve a joint task, such as pressing together a red or blue button, two (or more) agents engage in a process of interactive inference. Each agent maintains probabilistic beliefs about the joint goal (e.g., Should we press the red or blue button?) and updates them by observing the other agent’s movements, while in turn selecting movements that make his own intentions legible and easy to infer by the other agent (i.e., sensorimotor communication). Over time, the interactive inference aligns both the beliefs and the behavioral strategies of the agents, hence ensuring the success of the joint action. We exemplify the functioning of the model in two simulations. The first simulation illustrates a “leaderless” joint action. It shows that when two agents lack a strong preference about their joint task goal, they jointly infer it by observing each other’s movements. In turn, this helps the interactive alignment of their beliefs and behavioral strategies. The second simulation illustrates a “leader–follower” joint action. It shows that when one agent (“leader”) knows the true joint goal, it uses sensorimotor communication to help the other agent (“follower”) infer it, even if doing this requires selecting a more costly individual plan. These simulations illustrate that interactive inference supports successful multi-agent joint actions and reproduces key cognitive and behavioral dynamics of “leaderless” and “leader–follower” joint actions observed in human–human experiments. In sum, interactive inference provides a cognitively inspired, formal framework to realize cooperative joint actions and consensus in MAS.
Förderung
- MUR–PRIN2020
- EU Horizon 2020 Framework Programme for Research and Innovation through Human Brain Project SGA3 under the Specific
- TAILOR
- European Research Council through ThinkAhead
- PNRR MUR
Zitieren
APA
Maisto, D., Donnarumma, F., & Pezzulo, G. (2024). Interactive Inference: A Multi-Agent Model of Cooperative Joint Actions. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 54(2), 704-715. https://doi.org/10.1109/tsmc.2023.3312585
Vancouver
Maisto D, Donnarumma F, Pezzulo G. Interactive Inference: A Multi-Agent Model of Cooperative Joint Actions. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2024;54(2):704-715. doi:10.1109/tsmc.2023.3312585
BibTeX
@article{Maisto2024,
author = {Maisto, Domenico and Donnarumma, Francesco and Pezzulo, Giovanni},
title = {Interactive Inference: A Multi-Agent Model of Cooperative Joint Actions},
journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
year = {2024},
volume = {54},
number = {2},
pages = {704--715},
doi = {10.1109/tsmc.2023.3312585}
}
EUVIMED