Norm Conflict Resolution in Stochastic Domains

2017/06/22 by Daniel Kasenberg, Kasenberg, Daniel, Matthias Scheutz +1 · 3 citations
Computer Science · #Advanced Software Engineering Methodologies #FOS: Computer and information sciences #FOS: Electrical engineering #Formal Methods in Verification #Logic in Computer Science (cs.LO) #Logic, Reasoning, and Knowledge #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1706.07448

openalex publication_date 2017/06/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Artificial agents will need to be aware of human moral and social norms, and able to use them in decision-making. In particular, artificial agents will need a principled approach to managing conflicting norms, which are common in human social interactions. Existing logic-based approaches suffer from normative explosion and are typically designed for deterministic environments; reward-based approaches lack principled ways of determining which normative alternatives exist in a given environment. We propose a hybrid approach, using Linear Temporal Logic (LTL) representations in Markov Decision Processes (MDPs), that manages norm conflicts in a systematic manner while accommodating domain stochasticity. We provide a proof-of-concept implementation in a simulated vacuum cleaning domain.

Citations

• On the Logic of Normative Systems
• A Markovian Decision Process
• Robust Satisfaction of Temporal Logic Specifications via Reinforcement Learning

Cited by

• Deontically Constrained Policy Improvement in Reinforcement Learning Agents
• Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models
• HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning

Related

• Partially Observable Markov Decision Processes with Behavioral Norms
• A Defeasible Deontic Calculus for Resolving Norm Conflicts
• Towards a Logic of Graded Normativity and Norm Adherence
• Policy-Adaptable Methods For Resolving Normative Conflicts Through Argumentation and Graph Colouring
• Engaging in Dialogue about an Agent's Norms and Behaviors