I describe a suite of reinforcement learning environments in which artificial agents learn to value and respond to moral content and contexts. I illustrate the core principles of the framework by characterizing one such environment, or “gridworld,” in which an agent learns to trade-off between monetary profit and fair dealing, as applied in a standard behavioral economic paradigm. I then highlight the core technical and philosophical advantages of the learning approach for modeling moral cognition, and for addressing the so-called value alignment problem in AI.

中文翻译：

---

道德网格世界：模拟人工道德认知的理论建议

我描述了一套强化学习环境，在这些环境中，人工代理学会重视道德内容和环境并做出反应。我通过描述一个这样的环境或“网格世界”来说明该框架的核心原则，在这个环境中，代理学习在货币利润和公平交易之间进行权衡，如标准行为经济学范式所应用的那样。然后，我强调了建模道德认知和解决人工智能中所谓的价值对齐问题的学习方法的核心技术和哲学优势。