`Why didn't you allocate this task to them?' Negotiation-Aware Explicable Task Allocation and Contrastive Explanation Generation
This work addresses task allocation challenges in human-AI teams, offering incremental improvements in explicability and fairness through negotiation-aware methods.
The paper tackles the problem of task allocation in multi-agent systems with human team members who have imperfect knowledge, by proposing a centralized AI method that simulates negotiation to produce explicable allocations and generates contrastive explanations for counterfactuals. Results from human studies show that the allocation appears fair to the majority, and explanations are easy to comprehend and convincing, with empirical analysis indicating that underestimation of teammate costs increases explanation length.
Task allocation is an important problem in multi-agent systems. It becomes more challenging when the team-members are humans with imperfect knowledge about their teammates' costs and the overall performance metric. In this paper, we propose a centralized Artificial Intelligence Task Allocation (AITA) that simulates a negotiation and produces a negotiation-aware explicable task allocation. If a team-member is unhappy with the proposed allocation, we allow them to question the proposed allocation using a counterfactual. By using parts of the simulated negotiation, we are able to provide contrastive explanations that provide minimum information about other's cost to refute their foil. With human studies, we show that (1) the allocation proposed using our method appears fair to the majority, and (2) when a counterfactual is raised, explanations generated are easy to comprehend and convincing. Finally, we empirically study the effect of different kinds of incompleteness on the explanation-length and find that underestimation of a teammate's costs often increases it.