Causality, Responsibility and Blame in Team Plans
This addresses accountability in multi-agent systems, but it is incremental as it applies existing causal frameworks to team plans.
The paper tackles the problem of determining causality, responsibility, and blame when team plans fail, by representing plans with structural equations and applying existing definitions to compute these metrics, showing they can be determined in polynomial time for many cases.
Many objectives can be achieved (or may be achieved more effectively) only by a group of agents executing a team plan. If a team plan fails, it is often of interest to determine what caused the failure, the degree of responsibility of each agent for the failure, and the degree of blame attached to each agent. We show how team plans can be represented in terms of structural equations, and then apply the definitions of causality introduced by Halpern [2015] and degree of responsibility and blame introduced by Chockler and Halpern [2004] to determine the agent(s) who caused the failure and what their degree of responsibility/blame is. We also prove new results on the complexity of computing causality and degree of responsibility and blame, showing that they can be determined in polynomial time for many team plans of interest.