What Kind of Information Is Needed? Multi-Agent Reinforcement Learning that Selectively Shares Information from Other Agents

Riku Sakagami, Keiki Takadama, Keiki Takadama

2025

Abstract

Since agents' learning affects others' learning in multi-agent reinforcement learning (MARL), this paper aims to clarify what kind of information helps to improve learning of agents throgh complex interactions among them. For this purpose, this paper focuses on the information on observations/actions of other agents and analyzes its effect in MARL with the centralized training with decentralized execution (CTDE), which contributes to stabilizing agents' learning. Concretely, this paper extends the conventional MARL algorithm with CTDE (i.e., MADDPG in this research) to have the two mechanisms, each of which shares (i) information on observations of all agents; (ii) information on actions of all agents; and (iii) information on both the observations and actions of the selected agents. MARL with these three mechanisms is compared with MADDPG which shares information on both actions and observations of all agents and IDDPG which does not share any information. The experiments on multi-agent particle environments (MPEs) have revealed that the proposed method that selectively shares both observation and action information is superior to the other methods in both the full and partial observation environments where information on observations of all and selected agents.

Paper Citation

in Harvard Style

Sakagami R. and Takadama K. (2025). What Kind of Information Is Needed? Multi-Agent Reinforcement Learning that Selectively Shares Information from Other Agents. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 235-242. DOI: 10.5220/0013390100003890

in Bibtex Style

@conference{icaart25,
author={Riku Sakagami and Keiki Takadama},
title={What Kind of Information Is Needed? Multi-Agent Reinforcement Learning that Selectively Shares Information from Other Agents},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2025},
pages={235-242},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013390100003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - What Kind of Information Is Needed? Multi-Agent Reinforcement Learning that Selectively Shares Information from Other Agents
SN - 978-989-758-737-5
AU - Sakagami R.
AU - Takadama K.
PY - 2025
SP - 235
EP - 242
DO - 10.5220/0013390100003890
PB - SciTePress