Sequentially optimal repeated coalition formation under uncertainty

Abstract

Coalition formation is a central problem in multiagent systems research, but most models assume common knowledge of agent types. In practice, however, agents are often unsure of the types or capabilities of their potential partners, but gain information about these capabilities through repeated interaction. In this paper, we propose a novel Bayesian, model-based reinforcement learning framework for this problem, assuming that coalitions are formed (and tasks undertaken) repeatedly. Our model allows agents to refine their beliefs about the types of others as they interact within a coalition. The model also allows agents to make explicit tradeoffs between exploration (forming "new" coalitions to learn more about the types of new potential partners) and exploitation (relying on partners about which more is known), using value of information to define optimal exploration policies. Our framework effectively integrates decision making during repeated coalition formation under type uncertainty with Bayesian reinforcement learning techniques. Specifically, we present several learning algorithms to approximate the optimal Bayesian solution to the repeated coalition formation and type-learning problem, providing tractable means to ensure good sequential performance. We evaluate our algorithms in a variety of settings, showing that one method in particular exhibits consistently good performance in practice. We also demonstrate the ability of our model to facilitate knowledge transfer across different dynamic tasks.

Towards a Universal Test of Social Intelligence

“…But in any of these two cases it is not ensured that cooperation will occur. Alliances and coalitions [14,36,89,15,95] could arise sporadically between at least two agents in order to improve their rewards, probably by bothering or defending against a third agent. However, with low levels of social intelligence, alliances and coalitions seem unlikely to happen, since they would need some predisposed social abilities to maintain them in groups.…”

Dynamic constrained coalition formation among electric vehicles

“…However, the focus of their work is not to find optimal CSG solutions (the best CS), but optimal DCOP solutions (the correct value of the coalitions). Chalkiadakis and Boutilier [18] have proposed a Bayesian model-based reinforcement learning framework for repeated coalition formation under uncertainty. Such approach, however, is more concerned with agents' learning and decision-making and does not address the CSG problem.…”

Coalition formation based on marginal contributions and the Markov process

“…Second, the conflicts among agents are solved and the agents are grouped into coalitions according to their satisfaction degrees [17]. Third, the Markov chain combines two questions of stability with explicit monitoring of coalition formation [6].…”