Overlapping Coaltion Formation (OCF) is a relatively new paradigm that removes a restrictive assumption from the usual models studied in cooperative game theory, namely the assumption that agents can belong to
only one coalition at a time. Regardless, until recently the problem of uncertainty in OCF settings had been disregarded, with the focus being on studying rational behaviour from a traditional game-theoretic perspective. In this talk, I will present two recent works that initiate the study of uncertainty in OCF environments, via the computiation of probability bounds and the use of unsupervised learning techniques (in particular: probabilistic topic modelling) to enable rational agents’ decision making
in these complex domains.
This is joint work with my student Michalis Mamakos. Related papers:
1. *Probability Bounds for Overlapping Coalition Formation. *In Proc. of the 26th International Joint Conference on Artificial Intelligence (*IJCAI-2017*), Melbourne, Australia, August 2017.
http://www.intelligence.
tuc.gr/~gehalk/Papers/boundsocf.pdf
2. *Overlapping Coalition Formation via Probabilistic Topic Modeling. *In Proc. of the 17th Int. Conf. on Autonomous Agents and Multiagent Systems (*AAMAS-2018*), Stockholm, Sweden, July 2018.
https://arxiv.org/pdf/1804.05235.pdf
Contact person: Alessandro Farinelli