Procedural Creation of Behavior Trees for NPCs - Entertainment Computing Access content directly
Conference Papers Year : 2020

Procedural Creation of Behavior Trees for NPCs

Abstract

Based on an emerging need for automated AI generation, we present a machine learning approach to generate behavior trees controlling NPCs in a “Capture the Flag” game. After discussing the game’s mechanics and rule set, we present the implemented logic and how trees are generated. Subsequently, teams of agents controlled by generated trees are matched up against each other, allowing underlying trees to be refined by learning from victorious opponents. Following three program executions, featuring 1600, 8000 and 16000 matches, highest scoring trees are presented and discussed in this paper.
Fichier principal
Vignette du fichier
500145_1_En_26_Chapter.pdf (502.96 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03686014 , version 1 (02-06-2022)

Licence

Attribution

Identifiers

Cite

Robert Fronek, Barbara Göbl, Helmut Hlavacs. Procedural Creation of Behavior Trees for NPCs. 19th International Conference on Entertainment Computing (ICEC), Nov 2020, Xi'an, China. pp.285-296, ⟨10.1007/978-3-030-65736-9_26⟩. ⟨hal-03686014⟩
14 View
21 Download

Altmetric

Share

Gmail Facebook X LinkedIn More