一个具有社会意识的强化学习Agent在单线道路问题中的应用
A Socially Aware Reinforcement Learning Agent for The Single Track Road Problem
摘要:
我们提出了单轨道路问题。在这个问题中,两个代理人面对彼此在道路上的相对位置,一次只能有一个代理人通过。我们专注于其中一个代理人是人类,而另一个是一个自主智能体的情况。我们在一个简单的网格域,模拟单轨道路问题的人类受试者进行实验。我们表明,当数据是有限的,建立一个准确的人体模型是非常具有挑战性的,和一个强化学习代理,这是基于这些数据,并没有在实践中表现良好。然而,我们表明,代理人,试图最大限度地提高人类的效用和自己的效用的线性组合,实现了很高的分数,并显着优于其他基线,包括代理人,试图最大限度地提高自己的效用。
英文摘要:
We present the single track road problem. In this problem two agents face each-other at opposite positions of a road that can only have one agent pass at a time. We focus on the scenario in which one agent is human, while the other is an autonomous agent. We run experiments with human subjects in a simple grid domain, which simulates the single track road problem. We show that when data is limited, building an accurate human model is very challenging, and that a reinforcement learning agent, which is based on this data, does not perform well in practice. However, we show that an agent that tries to maximize a linear combination of the human's utility and its own utility, achieves a high score, and significantly outperforms other baselines, including an agent that tries to maximize only its own utility.
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。