JSAI2020

Presentation information

General Session

General Session » J-2 Machine learning

[2J6-GS-2] Machine learning: Advancement reinforcement learning (2)

Wed. Jun 10, 2020 5:50 PM - 7:30 PM Room J (jsai2020online-10)

座長:谷口忠大(立命館大学)

7:10 PM - 7:30 PM

[2J6-GS-2-05] Multi-Agent Deep Reinforcement Learning with Multi-Branch Networks Considering Interaction

〇Tsuyoshi Goto1, Tsubasa Hirakawa1, Takayoshi Yamashita1, Hironobu Fujiyoshi1 (1. Chubu University)

Keywords:Reinforcement Learning, Multi Agent, Interaction

When multiple agents are in the same environment, collisions may happen with each other. Because the agents consider their own interests or have a negative effect on other agents. In situation that happens these deadlocks, agents should select the action considering other agents based on multi-agent reinforcement learning which train multiple agents simultaneously. In this paper, we propose the method that trains multiple agents in a network with multi-branch network for this problem. It is possible to train an interaction between agents. In experiment, we build the environment that happens the deadlock between self-driving cars and compare with independent network of each agent. Moreover, we show the behavior of the agent in a deadlock situation.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password