A Study of Joint Policies Considering Bottlenecks and Fairness

Toshihiro Matsui

2019

Abstract

Multi-objective reinforcement learning has been studied as an extension of conventional reinforcement learning approaches. In the primary problem settings of multi-objective reinforcement learning, the objectives represent a trade-off between different types of utilities and costs for a single agent. Here we address a case of multiagent settings where each objective corresponds to an agent to improve bottlenecks and fairness among agents. Our major interest is how learning captures the information about the fairness with a criterion. We employ leximin-based social welfare in a single-policy, multi-objective reinforcement learning method for the joint policy of multiple agents and experimentally evaluate the proposed approach with a pursuit-problem domain.

Paper Citation

in Harvard Style

Matsui T. (2019). A Study of Joint Policies Considering Bottlenecks and Fairness.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-350-6, pages 80-90. DOI: 10.5220/0007577800800090

in Bibtex Style

@conference{icaart19,
author={Toshihiro Matsui},
title={A Study of Joint Policies Considering Bottlenecks and Fairness},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2019},
pages={80-90},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007577800800090},
isbn={978-989-758-350-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - A Study of Joint Policies Considering Bottlenecks and Fairness
SN - 978-989-758-350-6
AU - Matsui T.
PY - 2019
SP - 80
EP - 90
DO - 10.5220/0007577800800090