Requester vs. Helper-Initiated Protocols for Mutual Assistance in Agent Teamwork

The Mutual Assistance Protocol (MAP) enables members of an agent team to directly help each other whenever they jointly determine, through a bilateral distributed agreement, that such help is beneficial to the team. Its purpose is to improve the team's performance without affecting its existing organization. In this paper we define and investigate two versions of this generic protocol: the Requester-Initiated Action MAP, which enables team members to proactively seek help, and the Helper-Initiated Action MAP, which enables them to proactively offer help. In both cases, the help consists in performing an action on behalf of a teammate. We introduce the notions of individual well being, that helps an agent decide when to seek or offer help, and proximity bias, that favors assistance to agents which are close to an achievement for the team. Simulation experiments show that these design refinements result in team performance gains over the original version of Action MAP, as we vary the amount of agents' initial resources, dynamic disturbance in the environment, and communication costs. The results confirm the superior performance of teams with Action MAP protocols over teams without help mechanisms. The analysis shows that the relative strengths of the two protocols are complementary. This motivates research interest in protocols that allow proactive behavior of team members in both seeking and offering help.