Artificial Empathy: Towards a Framework for Unsupervised Agency Detection and Policy Reconstruction

2026-08-24

AI Summary

研究通过观察识别和建模环境中其他代理的问题，提出使用预先训练的强化学习代理进行代理检测和策略重构的方法。

Abstract

We study how an AI system can identify and model other agents in its environment from observation alone, which is a capability necessary for cooperative behaviour in the real world. This problem is less constrained than inverse reinforcement learning and remains largely unexplored. We propose a framework that uses a reinforcement learning agent, trained on an independent task as a prior about agentic dynamics, to perform agency detection and policy reconstruction.

Problem

• Artificial Empathy
• Agency Detection
• Policy Reconstruction

Innovation

• Unsupervised Agency Detection
• Policy Reconstruction
• Reinforcement Learning