Multi-Agent Archive-Based Inverse Reinforcement Learning by Improving Suboptimal Experts

Shunsuke Ueki, Keiki Takadama

2024

Abstract

This paper proposes the novel Multi-Agent Inverse Reinforcement Learning method that can acquire reward functions in continuous state space by improving the “suboptimal” expert behaviors. Specifically, the proposed method archives the superior “individual” behaviors of the agent without taking an account of other agents, selects the “cooperative” behaviors that can cooperate with other agents from the individual behaviors, and improve expert behaviors according to both the individual and cooperative behaviors to obtain the better behaviors of the agents than those of experts. The experiments based on the maze problem in a continuous state space have been revealed the following implications (1) the suboptimal expert trajectories that may collide with the other agents can be improved to the trajectories that can avoid the collision among the agents; and (2) the number of collisions of agents and the expected return in the proposed method is smaller/larger than those in MA-GAIL and MA-AIRL.

Paper Citation

in Harvard Style

Ueki S. and Takadama K. (2024). Multi-Agent Archive-Based Inverse Reinforcement Learning by Improving Suboptimal Experts. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 1362-1369. DOI: 10.5220/0012475100003636

in Bibtex Style

@conference{icaart24,
author={Shunsuke Ueki and Keiki Takadama},
title={Multi-Agent Archive-Based Inverse Reinforcement Learning by Improving Suboptimal Experts},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1362-1369},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012475100003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Multi-Agent Archive-Based Inverse Reinforcement Learning by Improving Suboptimal Experts
SN - 978-989-758-680-4
AU - Ueki S.
AU - Takadama K.
PY - 2024
SP - 1362
EP - 1369
DO - 10.5220/0012475100003636
PB - SciTePress