Resource-Aware Adaptation of Heterogeneous Strategies for Coalition Formation

Existing approaches to coalition formation assume that task requirements are precisely specified by the human operator. Further, existing approaches ignore the fact that tasks could often be performed by following one of many equivalent strategies. However, prior work has demonstrated that humans, while extremely adept at solving complex problems, struggle to explicitly state the intuition that led to their solution. In this work, we propose a two-part framework to i) learn implicit heterogeneous strategies for coalition formation directly from expert demonstrations, and ii) adaptively select one of the inferred strategies based on available resources, without additional training.