A Socially Aware Reinforcement Learning Agent for The Single Track Road Problem

TL;DR

This paper investigates a reinforcement learning approach for a single track road scenario involving human and autonomous agents, highlighting challenges in modeling human behavior and proposing a utility-based agent that improves performance.

Contribution

It introduces a socially aware reinforcement learning agent that balances human and autonomous utilities, outperforming traditional self-interested agents in the single track road problem.

Findings

Modeling human behavior with limited data is challenging.

Utility-based agents outperform self-interested agents.

The proposed agent achieves higher scores in experiments.

Abstract

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.