Requirements for Aligned, Dynamic Resolution of Conflicts in Operational Constraints

Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios where no available course of action fully satisfies all operational constraints (e.g., operating procedures, rules, laws, norms, and goals). To achieve goals in accordance with human expectations and values, agents must go beyond their trained policies and instead construct, evaluate, and justify candidate courses of action. These processes require contextual "knowledge" that may lie outside prior (policy) training. This paper characterizes requirements for agent decision making in these contexts. It also identifies the types of knowledge agents require to make decisions robust to agent goals and aligned with human expectations. Drawing on both analysis and empirical case studies, we examine how agents need to integrate normative, pragmatic, and situational understanding to select and then to pursue more aligned courses of action in complex, real-world environments.

Heuristic Recognition and Rapid Response to Unfamiliar Events Outside of Agent Design Scope

Regardless of past learning, an agent in an open world will face unfamiliar situations and events outside of prior experience, existing models, or policies. Further, the agent will sometimes lack relevant knowledge and/or sufficient time to assess the situation, generate and evaluate options, and pursue a robustly considered course of action. How can an agent respond reasonably to situations that are outside of its original design scope? How can it recognize such situations sufficiently quickly and reliably to determine reasonable, adaptive courses of action? We identify key characteristics needed for solutions, evaluate the state-of-the-art by these requirements, and outline a proposed, novel approach that combines domain-general meta-knowledge (in the form of appraisals inspired by human cognition) and metareasoning. It has the potential to provide fast, adaptive responses to unfamiliar situations, more fully meeting the performance characteristics required for open-world, general agents.