go back

Quantifying cooperation between artificial agents using synergistic information

Patricia Wollstadt and Matti Krüger, "Quantifying cooperation between artificial agents using synergistic information", 2022 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1044-1051, 2023.


When designing interactive human-machine sys- tems, it is often assumed that it is desirable for such systems to behave cooperatively towards a human operator in order to improve trust, acceptance, and usability, but also to increase task effi ciency. To design cooperative human-machine interaction (HMI) systems, we have to be able to defi ne and quantitatively describe cooperative behavior, for example, to control, optimize, or evaluate the interaction. Despite the increased interest in cooperative HMI in recent years, an approach that provides a suitable defi nition of cooperation and also a method for its quantifi cation is still missing. In the present work, we therefore develop a novel defi nition of cooperative behavior in HMI con- texts, based on which we propose to quantify cooperation using recent methods from information theory. We defi ne cooperation as joint, coordinated actions that are mutually adapted such as to facilitate the realization of a goal. Thus, cooperation is characterized by a synergistic effect of joint actions towards the goal. Here, we propose to quantify cooperation using the recently introduced partial information decomposition framework from information theory, which proposes measures to quantify the synergistic contributions of two inputs to a target variable. In particular, we propose to apply the synergy measure to two or more input variables describing agents’ actions towards a target variable that describes the current goal state. As a fi rst validation, we applied our approach in a grid-world environment, in which two agents solve a cooperative foraging task. We found that synergy was higher for agents implementing cooperative strategies compared to baseline and non-cooperative strategies, and we found higher synergy in trials with high numbers of cooperative actions. We conclude that the synergy is a promising candidate measure for identifying cooperative behavior in goal- oriented interactions.

Download Bibtex file Download PDF