用多目标强化学习实现多方价值对齐，让AI更公平地兼顾不同利益。
Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment
- 用向量奖励替代单一数值奖励，同时优化多个目标。
- 可有效处理存在冲突价值观或利益相关方的复杂场景。
- 适合需要平衡多元诉求的AI系统设计，如政策制定、医疗决策。
强化学习（RL）是构建人工智能系统的重要工具，但在存在多个相互冲突的价值观或利益相关方时，仅依赖标量奖励进行对齐可能效果不佳。过去十年中，采用向量奖励的多目标强化学习（MORL）逐渐成为标准标量强化学习的替代方案。本文综述了MORL在实现多元共治对齐方面的潜力，探讨其在构建兼顾多方诉求的智能系统中的关键作用。
原文摘要 · Abstract (English)
Reinforcement learning (RL) is a valuable tool for the creation of AI systems. However it may be problematic to adequately align RL based on scalar rewards if there are multiple conflicting values or stakeholders to be considered. Over the last decade multi-objective reinforcement learning (MORL) using vector rewards has emerged as an alternative to standard, scalar RL. This paper provides an overview of the role which MORL can play in creating pluralistically-aligned AI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。