概要

This paper establishes directionality reinforcement learning (DRL) technique to propose the complete decentralized multi-agent reinforcement learning method which can achieve cooperation based on each agent’s learning: no communication and no observation. Concretely, DRL adds the direction “agents have to learn to reach the farthest goal among reachable ones” to learning agents to operate the agents cooperatively. Furthermore, to investigate the effectiveness of the DRL, this paper compare Q-learning agent with DRL with previous learning agent in maze problems. Experimental results derive that (1) DRL performs better than the previous method in terms of the spending time, (2) the direction makes agents learn yielding action for others, and (3) DRL suggests achieving multi-agent learning with few costs for any number of agents.

論文誌情報

題目: Directionality Reinforcement Learning to Operate Multi-Agent System without Communication
著者: Fumito Uwano and Keiki Takadama
誌名: Proceedings of the 11th AAMAS workshop on Optimization and Learning in Multiagent Systems (OptLearnMAS2020)
詳細: Auckland, New Zealand, May 2020

Bibtex or Download

@inproceedings{fumito uwano 2020directionality,
  title={Directionality Reinforcement Learning to Operate Multi-Agent System without Communication},
  author={Fumito Uwano and Keiki Takadama},
  booktitle={Proceedings of the 11th AAMAS workshop on Optimization and Learning in Multiagent Systems (OptLearnMAS2020)},
  year={2020},
  pages={},
  month={May}
}