Automatic generation of tower defense levels using PCG

Abstract

Tower defense is a popular subgenre of real-time strategy game requiring detailed level design and difficulty balancing to create an enjoyable player experience. Because level production and testing are both time-consuming and labor-intensive, we propose and implement a framework to automate the process. We first analyze the three main components, or "building blocks", of the popular tower defense game Kingdom Rush: Frontiers (KRF), i.e. road maps, tower locations and monster sequences. We then automatically create new building blocks in the style of the original game, utilizing techniques from Procedural Content Generation (PCG), and assemble them to create new levels. We also add a fourth block: automated testing via a Monte Carlo search algorithm, to ensure the generated content is playable. We focus on KRF because it is a popular video game in the tower defense genre, and highlights some of the challenges of designing appropriate PCG and playtesting algorithms for a commercial video game.

Assessing Video Game Balance using Autonomous Agents

“…Liu, Chaoran, Yue, et al [13] used procedural content generation to create new tower defense game levels to then playtest it autonomously using flat MCTS. Morosan and Poli [14], [15] used evolutionary algorithm to balance different games, like Pacman and StarCraft, using the win-rate as oracle.…”

Procedural Content Generation pada Game Tower Defense menggunakan Perlin Noise dan Algoritma Floyd Warshall

“…Dalam mendesain map untuk game tower defense harus ada 3 elemen standar, yaitu map yang dibuat harus memiliki rute perjalanan musuh dari titik awal menuju titik tujuan, memiliki tantangan yang cukup dari urutan monster yang di spawn, dan dari jenis tower yang dapat dibangun (Du et al, 2019). Proses yang perlu dilakukan saat pembuatan map untuk game tower defense yaitu proses mendesain map itu sendiri, mendesain lokasi setiap tower, mendesain gambar yang digunakan, mendesain rute perjalanan monster, dan melakukan uji coba terhadap map apakah dapat dimainkan atau tidak (Liu et al, 2019).…”