Online and Hierarchical Agent Supervision

Agent supervision is a form of control/customization where a supervisor restricts the behavior of an agent to enforce certain requirements, while leaving the agent as much autonomy as possible. This framework is based on the situation calculus and a variant of the ConGolog agent programming language. In this dissertation, we focus on two of the open problems with the original account of agent supervision. The first open problem is supervising an agent that may acquire new knowledge about her environment during an online execution, for example, by sensing. The second open problem concerns the supervision of agents that operate in complex domains and have complex behavior. Such agents typically need to represent and reason about a large amount of knowledge. One approach to cope with this challenge is to use abstraction, which involves developing an abstract/high-level model of the agent behavior that suppresses less important details. Hence, we first investigate abstracting an agent's behavior in offline executions, and formalize a notion of sound and/or complete abstractions. Sound abstractions can be used to perform several forms of reasoning about action, such as planning, agent monitoring, and generating high-level explanations of low-level/concrete agent behavior. Moreover, we investigate abstraction of agent's behavior in online executions, and discuss its relation to hierarchical contingent planning. We then use our results on offline agent abstraction to formalize hierarchical agent supervision: in a first step, we only consider the high-level model and obtain the maximally permissive supervisor to customize the abstract agent behavior; then in a second step, we obtain a low-level supervisor by refining the high-level supervisor's actions locally. We show that this process can be done incrementally, without precomputing the local refinements.