JSAI2024

Presentation information

Poster Session

Poster session » Poster session

[3Xin2] Poster session 1

Thu. May 30, 2024 11:00 AM - 12:40 PM Room X (Event hall 1)

[3Xin2-73] An Embedding-Based Optimization Approach for Idol Unit Formation in "IDOLY PRIDE"

〇Koya Ihara1, Kazunori Tamura2, Yingrui Ye1, Masahiro Nomura1 (1.CyberAgent Inc., 2.QualiArts, Inc.)

Keywords:Digital Game, IDOLY PRIDE, Combinatorial Optimization, Genetic Algorithm, Embedding

The most critical aspect of gameplay in the smartphone RPG (role-playing game) "IDOLY PRIDE" involves live unit formation. It is important to find the appropriate unit formation is important to assess the effect of new idols before their implementation in the game.
In this work, we formulate the unit formation as a combinatorial optimization problem, and then develop a new genetic algorithm (GA) for efficiently solving this problem. We develop idol representations by embedding preliminary information of the idols and use them for developing a mutation operator over the embedding space.
The experiments in a simulation environment of IDOLY PRIDE demonstrate the effectiveness of applying the GA and introducing the proposed mutation operator.

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