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.

中文翻译：

---

单轨道路问题的社会意识强化学习代理

我们提出了单轨道路问题。在这个问题中，两个代理在一条道路的相对位置面对面，一次只能让一个代理通过。我们专注于一个代理是人类而另一个是自主代理的场景。我们在一个简单的网格域中对人类受试者进行实验，模拟单轨道路问题。我们表明，当数据有限时，构建准确的人体模型非常具有挑战性，并且基于这些数据的强化学习代理在实践中表现不佳。然而，我们表明，试图最大化人类效用和自身效用的线性组合的代理获得了高分，并且明显优于其他基线，包括试图仅最大化其自身效用的代理。