A normative supervisor is an external module that uses a formal reasoning engine to impose normative constraints on re inforcement learning agents, by either dynamic action masking or feeding the agent additional punishments when violations of norms occur (or both). In this paper, we use a normative supervisor implemented with a solver for deontic answer set programming (ASP) — deolingo — as a basis for the construction of a normative narrator, which uses deolingo’s ability to interface with the explainable solver xclingo to construct a module capable of both regulating behaviour through action masking and additional punishments, and providing contrastive explanations of why a given action was allowed while others were not, relative to the normative system being enforced. The explanations are modelled after the two tiers – internal and external – of explanation. We demonstrate this approach’s ability to provide understandable and descriptive explanations in a scenario where a taxi driver agent must act in accordance to a normative system governing its normal duties and provisions that must be made in case of an emergency.

Normative Restraining Bolts (NRBs) adapt the restraining bolt technique (originally developed for safe reinforcement learning) to ensure compliance with social, legal, and ethical norms. While effective, NRBs rely on trial-and-error weight tuning, which hinders their ability to enforce hierarchical norms; moreover, norm updates require retraining. In this paper, we reformulate learning with NRBs as a multi-objective reinforcement learning (MORL) problem, where each norm is treated as a distinct objective. This enables the introduction of Ordered Normative Restraining Bolts (ONRBs), which support algorithmic weight selection, prioritized norms, norm updates, and provide formal guarantees on minimizing norm violations. Case studies show that ONRBs offer a robust and principled foundation for RL-agents to comply with a wide range of norms while achieving their goals.

We modify the restraining bolt technique, originally designed for safe reinforcement learning, to regulate agent behavior in alignment with social, ethical, and legal norms. Rather than maximizing rewards for norm compliance, our approach minimizes penalties for norm violations. We demonstrate in case studies the effectiveness of our approach in capturing benchmark challenges in normative reasoning like contrary-to-duty obligations, exceptions, and temporal obligations.

Reinforcement learning (RL) has shown promise as a tool for engineering safe, ethical, or legal behaviour in autonomous agents. Its use typically relies on assigning punishments to state-action pairs that constitute unsafe or unethical choices. Despite this assignment being a crucial step in this approach, however, there has been limited discussion on generalizing the process of selecting punishments and deciding where to apply them. In this paper, we adopt an approach that leverages an existing framework -- the normative supervisor of (Neufeld et al., 2021) -- during training. This normative supervisor is used to dynamically translate states and the applicable normative system into defeasible deontic logic theories, feed these theories to a theorem prover, and use the conclusions derived to decide whether or not to assign a punishment to the agent. We use multi-objective RL (MORL) to balance the ethical objective of avoiding violations with a non-ethical objective; we will demonstrate that our approach works for a multiplicity of MORL techniques, and show that it is effective regardless of the magnitude of the punishment we assign.

Abstract We introduce a modular and transparent approach for augmenting the ability of reinforcement learning agents to comply with a given norm base. The normative supervisor module functions as both an event recorder and real-time compliance checker w.r.t. an external norm base. We have implemented this module with a theorem prover for defeasible deontic logic, in a reinforcement learning agent that we task with playing a “vegan” version of the arcade game Pac-Man.