Norm Conflict Resolution in Stochastic Domains
This work provides a principled method for managing conflicting norms in stochastic domains, relevant for AI systems interacting with humans.
The paper addresses norm conflict resolution for artificial agents in stochastic environments, proposing a hybrid approach using LTL in MDPs. A proof-of-concept is demonstrated in a simulated vacuum cleaning domain.
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.