用多道德框架解决不确定情境下的伦理决策问题
Uncertain Machine Ethics Planning
- 将伦理决策建模为多道德马尔可夫决策过程，融合多种道德理论
- 提出基于多目标AO*的启发式算法，在不确定性下实现道德权衡
- 案例验证表明能有效处理如'是否偷药'等复杂伦理困境
机器伦理决策需考虑不确定性带来的影响。决策应基于行动序列以达成长期可取结果。然而，结果评估可能涉及一个或多个道德理论，这些理论可能产生冲突判断。每种理论对伦理情境的表示方式不同：功利主义关注数值效用，义务论分析责任，美德伦理强调道德品质。在权衡潜在冲突的道德考量时，需做出决策，例如以最小代价实现道德中立目标。本文将该问题形式化为多道德马尔可夫决策过程（Multi-Moral MDP）与多道德随机最短路径问题（Multi-Moral SSP）。我们基于多目标AO*开发了一种启发式算法，并采用Sven-Ove Hansson的假设回溯法进行不确定性下的伦理推理。通过机器伦理文献中的经典案例——是否为急需者偷取胰岛素——进行验证。
原文摘要 · Abstract (English)
Machine Ethics decisions should consider the implications of uncertainty over decisions. Decisions should be made over sequences of actions to reach preferable outcomes long term. The evaluation of outcomes, however, may invoke one or more moral theories, which might have conflicting judgements. Each theory will require differing representations of the ethical situation. For example, Utilitarianism measures numerical values, Deontology analyses duties, and Virtue Ethics emphasises moral character. While balancing potentially conflicting moral considerations, decisions may need to be made, for example, to achieve morally neutral goals with minimal costs. In this paper, we formalise the problem as a Multi-Moral Markov Decision Process and a Multi-Moral Stochastic Shortest Path Problem. We develop a heuristic algorithm based on Multi-Objective AO*, utilising Sven-Ove Hansson's Hypothetical Retrospection procedure for ethical reasoning under uncertainty. Our approach is validated by a case study from Machine Ethics literature: the problem of whether to steal insulin for someone who needs it.
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。