让AI做道德决定时能考虑正当理由，避免机械执行指令
Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents
- 用基于理由的防护罩约束智能体行为
- 通过道德评判反馈迭代优化防护机制
- 适合研究可解释伦理决策的AI系统
我们提出一种强化学习架构的扩展，使智能体能够基于规范性理由做出道德决策。该方法的核心是一个基于理由的防护罩生成器，生成的道德防护罩将智能体限制在符合公认规范性理由的行动上，从而确保其整体行为在内部具有道德正当性。此外，我们设计了一种算法，通过来自道德评判者的案例反馈，迭代改进该防护罩生成器。
原文摘要 · Abstract (English)
We propose an extension of the reinforcement learning architecture that enables moral decision-making of reinforcement learning agents based on normative reasons. Central to this approach is a reason-based shield generator yielding a moral shield that binds the agent to actions that conform with recognized normative reasons so that our overall architecture restricts the agent to actions that are (internally) morally justified. In addition, we describe an algorithm that allows to iteratively improve the reason-based shield generator through case-based feedback from a moral judge.
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。