[2G4-OS-21d] 世界モデルと知能

[2G4-OS-21d-02] World Model Based Multi-Agent Reinforcement Learning for Path Planning Considering Fairness Among Agents

Mizuho Aoki¹, Temma Fujishige², 〇Kei Tsukamoto³, Masaya Fujimoto⁴, Masahiro Suzuki⁵, Yutaka Matsuo⁵ (1. Graduate School of Engineering, Nagoya University , 2. School of Life Science and Technology, Tokyo Institute of Technology, 3. The University of Tokyo, 4. Graduate School of Infomation Science and Technology, Osaka University, 5. Graduate School of Engineering, the University of Tokyo)

Keywords:World Model, Fairness

Research on multi-agent path planning using reinforcement learning methods has recently been developed. However, a common problem in this field is the difficulty of agents learning to cooperate with each other, since each agent is motivated by its own reward. In this study, we examined the impact of considering not only self-reward but also those of others. A world model is introduced to predict the future states of the environment. Considering agents' fairness is expected to be an effective solution to address reward bias among agents and ultimately achieve satisfactory performance in real-world applications, such as operating in crowded environments.