Reinforcement Learning Guided by Provable Normative Compliance

2022-03-30 · Emery Neufeld

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.

📄 PDF Abstract BibTeX arXiv:2203.16275

Code (1)

lexeree/normative-player-characters 공식 구현

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A Four-Valued Normative Intermediate Representation for ASP-Oriented Compliance Reasoning

2026-06-03 · Huanyu Yang, Yangfan Wu, Jianmin Ji arxiv

Technical-standard compliance reasoning may involve incomplete evidence, inconsistent observations, exceptions, and derived normative outputs. This paper presents \textsc{Monir}, a four-valued normative intermediate repr…

GraphCompliance: Aligning Policy and Context Graphs for LLM-Based Regulatory Compliance

2025-10-30 · Jiseong Chung, Ronny Ko, Wonchul Yoo, Makoto Onizuka 외 arxiv

Compliance at web scale poses practical challenges: each request may require a regulatory assessment. Regulatory texts (e.g., the General Data Protection Regulation, GDPR) are cross-referential and normative, while runti…

Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings

2023-05-26 · Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo

This paper proposes the Phy-DRL: a physics-regulated deep reinforcement learning (DRL) framework for safety-critical autonomous systems. The Phy-DRL has three distinguished invariant-embedding designs: i) residual action…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning

Reinforcing privacy reasoning in LLMs via normative simulacra from fiction

2026-04-21 · Matt Franchi, Madiha Zahrah Choksi, Harold Triedman, Helen Nissenbaum arxiv

Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI) provides a principled framework, defining privacy as the appropriate …

Reinforcement Learning

Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models

2026-02-12 · Alexander W. Goodall, Francesco Belardinelli arxiv

Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we introduce a novel recovery-based shieldi…

Reinforcement Learning Continuous Control