基于探测的Agent行为干预
Probe-Based Interventions for Modifying Agent Behavior
摘要：
神经网络是功能强大的函数逼近器，但给定神经网络的行为一旦训练好，就不能轻易修改。然而，我们希望人们能够影响神经代理的行为，尽管这些代理从未与人类一起训练过，我们将其形式化为人类辅助决策问题。受最初为模型可解释性开发的现有技术的启发，我们开发了一种根据外部指定的属性更新预训练神经网络中的表示的方法。在实验中，我们展示了如何使用我们的方法来提高人类代理团队的性能，从图像分类器到多智能体强化学习设置中的代理的各种神经网络。
英文摘要：
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified. We wish, however, for people to be able to influence neural agents' actions despite the agents never training with humans, which we formalize as a human-assisted decision-making problem. Inspired by prior art initially developed for model explainability, we develop a method for updating representations in pre-trained neural nets according to externally-specified properties. In experiments, we show how our method may be used to improve human-agent team performance for a variety of neural networks from image classifiers to agents in multi-agent reinforcement learning settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
