PapeRman #6

本文描述了一个新的推断智能体动机的方法。该方法基于影响图，这是一种图模型的类型，包含特别的决策和效用节点。图标准可以被用来确智能体观测动机和智能体干预动机**

Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings

Tom Everitt Pedro A. Ortega Elizabeth Barnes Shane Legg
Deepmind

Abstract

Agents are systems that optimize an objective function in an environment. Together, the goal and the environment induce secondary objectives, incentives. Modeling the agent-environment interaction in graphical models called influence diagrams, we can answer two fundamental questions about an agent's incentives directly from the graph: (1) which nodes is the agent incentivized to observe, and (2) which nodes is the agent incentivized to influence? The answers tell us which information and influence points need extra protection. For example, we may want a classifier for job applications to not use the ethnicity of the candidate, and a reinforcement learning agent not to take direct control of its reward mechanism. Different algorithms and training paradigms can lead to different influence diagrams, so our method can be used to identify algorithms with problematic incentives and help in designing algorithms with better incentives.