TY - GEN
T1 - Autonomous Agents for The Single Track Road Problem
AU - Shapira, Ido
AU - Azaria, Amos
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - Autonomous vehicles
KW - Human agent
KW - Human modeling
KW - Reinforcement Learning
KW - interaction
UR - http://www.scopus.com/inward/record.url?scp=85123956095&partnerID=8YFLogxK
U2 - 10.1109/ICTAI52525.2021.00019
DO - 10.1109/ICTAI52525.2021.00019
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85123956095
T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
SP - 81
EP - 85
BT - Proceedings - 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence, ICTAI 2021
PB - IEEE Computer Society
T2 - 33rd IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2021
Y2 - 1 November 2021 through 3 November 2021
ER -