Autonomous Agents and Policy Compliance: A Framework for Reasoning About Penalties
This work addresses the challenge of balancing policy compliance with goal achievement in autonomous systems, offering a tool for policymakers to simulate realistic decision-making, though it is incremental as it builds on existing AOPL and ASP methods.
The paper tackles the problem of enabling autonomous agents to reason about penalties for policy non-compliance, presenting a logic programming-based framework that extends AOPL with penalty-based reasoning and ASP integration, resulting in higher-quality plans that avoid harmful actions and sometimes improve computational efficiency.
This paper presents a logic programming-based framework for policy-aware autonomous agents that can reason about potential penalties for non-compliance and act accordingly. While prior work has primarily focused on ensuring compliance, our approach considers scenarios where deviating from policies may be necessary to achieve high-stakes goals. Additionally, modeling non-compliant behavior can assist policymakers by simulating realistic human decision-making. Our framework extends Gelfond and Lobo's Authorization and Obligation Policy Language (AOPL) to incorporate penalties and integrates Answer Set Programming (ASP) for reasoning. Compared to previous approaches, our method ensures well-formed policies, accounts for policy priorities, and enhances explainability by explicitly identifying rule violations and their consequences. Building on the work of Harders and Inclezan, we introduce penalty-based reasoning to distinguish between non-compliant plans, prioritizing those with minimal repercussions. To support this, we develop an automated translation from the extended AOPL into ASP and refine ASP-based planning algorithms to account for incurred penalties. Experiments in two domains demonstrate that our framework generates higher-quality plans that avoid harmful actions while, in some cases, also improving computational efficiency. These findings underscore its potential for enhancing autonomous decision-making and informing policy refinement. Under consideration in Theory and Practice of Logic Programming (TPLP).