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

arXiv: https://arxiv.org/abs/2109.05486 · HTML: https://mlsanity.com/paper/2109.05486/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 35 references that are in the map.
- First posted on arXiv 12 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [Convolutional Social Pooling for Vehicle Trajectory Prediction](https://mlsanity.com/paper/1805.06771/) (2018)
- [Probabilistic Vehicle Trajectory Prediction over Occupancy Grid Map via Recurrent Neural Network](https://mlsanity.com/paper/1704.07049/) (2017)
- [Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs](https://mlsanity.com/paper/1912.01118/) (2019)
- [A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving](https://mlsanity.com/paper/1909.07707/) (2019)
- [Predicting Vehicle Behaviors Over An Extended Horizon Using Behavior Interaction Network](https://mlsanity.com/paper/1903.00848/) (2019)
- [Predicting Human Cooperation](https://mlsanity.com/paper/1601.07792/) (2016)

## Abstract (arXiv)

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.