论文标题
发现代理
Discovering Agents
论文作者
论文摘要
代理的因果模型已用于分析机器学习系统的安全性方面。但是，识别代理是非平凡的 - 通常只是由建模者假设而没有太多理由的原因 - 建模失败可能会导致安全分析中的错误。本文提出了对代理商的第一个正式因果定义 - 大约是代理人是制度，如果他们的行动以不同的方式影响世界，则可以改善其政策。由此，我们得出了第一个用于从经验数据中发现代理的因果发现算法，并提供了用于在因果模型和游戏理论影响图之间转换的算法。我们通过解决因素不正确的因果模型引起的一些先前的困惑来证明我们的方法。
Causal models of agents have been used to analyse the safety aspects of machine learning systems. But identifying agents is non-trivial -- often the causal model is just assumed by the modeler without much justification -- and modelling failures can lead to mistakes in the safety analysis. This paper proposes the first formal causal definition of agents -- roughly that agents are systems that would adapt their policy if their actions influenced the world in a different way. From this we derive the first causal discovery algorithm for discovering agents from empirical data, and give algorithms for translating between causal models and game-theoretic influence diagrams. We demonstrate our approach by resolving some previous confusions caused by incorrect causal modelling of agents.
