Multi-Value Alignment in Normative Multi-Agent System: Evolutionary Optimisation Approach
Value-alignment in normative multi-agent systems is used to promote a certain value and to ensure the consistent behavior of agents in autonomous intelligent systems with human values. However, the current literature is limited to incorporation of effective norms for single value alignment with no consideration of agents' heterogeneity and the requirement of simultaneous promotion and alignment of multiple values. This research proposes a multi-value promotion model that uses multi-objective evolutionary algorithms to produce the optimum parametric set of norms that is aligned with multiple simultaneous values of heterogeneous agents and the system. To understand various aspects of this complex problem, several evolutionary algorithms were used to find a set of optimised norm parameters considering two toy tax scenarios with two and five values are considered. The results are analysed from different perspectives to show the impact of a selected evolutionary algorithm on the solution, and the importance of understanding the relation between values when prioritising them.
Code (0)
등록된 구현이 없습니다.
Tasks
Evolutionary AlgorithmsSimilar Papers 제목 키워드 기반
Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior
As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Learning Norms from Stories: A Prior for Value Aligned Agents
Value alignment is a property of an intelligent agent indicating that it can only pursue goals and activities that are beneficial to humans. Traditional approaches to value alignment use imitation learning or preference …
Imitation LearningEnhancing Value Alignment of LLMs with Multi-agent system and Combinatorial Fusion
Aligning large language models (LLMs) with human values is a central challenge for ensuring trustworthy and safe deployment. While existing methods such as Reinforcement Learning from Human Feedback (RLHF) and its varian…
Reinforcement LearningThe Goofus & Gallant Story Corpus for Practical Value Alignment
Values or principles are key elements of human society that influence people to behave and function according to an accepted standard set of social rules to maintain social order. As AI systems are becoming ubiquitous in…
Beyond Preferences in AI Alignment
The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values, (2) that human rationality can be understood in terms of maximizing the satisfaction of preferences, and …
Descriptive