Ad hoc Teamwork and Moral Feedback as a Framework for Safe Agent Behavior
share
As technology develops, it is only a matter of time before agents will be capable of long term autonomy, i.e., will need to choose their actions by themselves for a long period of time. Thus, in many cases agents will not be able to be coordinated in advance with all other agents with which they may interact. Instead, agents will need to cooperate in order to accomplish unanticipated joint goals without pre-coordination. As a result, the "ad hoc teamwork" problem, in which teammates must work together to obtain a common goal without any prior agreement regarding how to do so, has emerged as a recent area of study in the AI literature. However, to date, no attention has been dedicated to the moral aspect of the agents' behavior, which is required to ensure that their actions' influences on other agents conform with social norms. In this research, we introduce the M-TAMER framework (a novel variant of TAMER) used to teach agents to act in accordance with human morality with respect to their teammates. Using a hybrid team (agents and people), if taking an action considered to be morally unacceptable, the agents will receive negative feedback from the human teammate(s). Using M-TAMER, agents will learn to act more consistently with respect to human morality.
READ FULL TEXT