Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Game AI Agents using Deliberative Behavior Tree based on Utility Theory

효용이론 기반 숙고형 행동트리를 이용한 게임 인공지능 에이전트

  • Kwon, Minji (Game Animation Engineering Major, Dong-eui University) ;
  • Seo, Jinsek (Game Engineering Major, Dong-eui University)
  • Received : 2022.02.11
  • Accepted : 2022.02.23
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

This paper introduces deliberative behavior tree using utility theory. The proposed approach combine the strengths of behavior trees and utility theory to implement complex behavior of AI agents in an easier and more concise way. To achieve this goal, we devised and implemented three types of additional behavior tree nodes, which evaluate utility values of its own node or its subtree while traversing and selecting its child nodes based on the evaluated values. In order to validate our approach, we implemented a sample scenario using conventional behavior tree and our proposed deliberative tree respectively. And then we compared and analyzed the simulation results.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT). (No. NRF-2019R1F1A1041854)

References

  1. M. Dawe, S. Gargolinski, L. Dicken, T. Humphreys, and D. Mark, "Behavior Selection Algorithms An: Overview," Game AT Pro: Collected Wisdom of Game AI Professionals, A K Peters/CRC Press, pp. 47-60, 2013.
  2. D. Hilbum, "Simulating Behavior Trees: A Behavior Tree/Planner Hybrid Approach," Game AI Pro: Collected Wisdom of Game AI Professionals, A K Peters/CRC Press, pp. 99-111, 2013.
  3. Handling Complexity in the Halo 2 AI(2005), https:j/www.gamedeveloper.com/programming/gdc-2005-proceeding-handling-complexity-in-the-i-halo-2-i-ai (accessed February 1, 2022).
  4. Building a Better Battle: HALO 3 AI Objectives, https://aarmstrong.org/files/gdc2008/Building%20a%20Better%20Battle%20HALO%203%20AI%20Objectives.pdf (accessed February 1, 2022).
  5. D.R Graham, "An Introduction to Utility Theory," Game AI Pro: Collected Wisdom of Game AI Professionals, A K Peters/CRC Press, pp. 113-126, 2013.
  6. Unity Technologies, Animation System Overview, https:j/docs.unity3d.com/Manual/AnimationOverview.html (accessed February 2, 2022).
  7. Epic Games, "Behavior Trees," https://docs.unrealengine.com/en-US/Engine/ArtificialIntelligence/BehaviorTrees/index.html (accessed February 2, 2022).
  8. M. Colledanchise and P. Ogren, Behavior Trees in Robotics and AI: An Introduction, CRC Press, 2018.
  9. A. Shoulson, F.M. Garcia, M. Jones, R. Mead, and N.I. Badler, "Parameterizing behavior trees," International Conference on Motion in Games, pp. 144-155, 2011.
  10. J. Seo and U. Yang, "Procedural Behavior Model using Behavior Tree in Virtual Reality Applications," Journal of Multimedia Information system, Vol. 6, No. 4, pp. 179-184, 2019. https://doi.org/10.33851/JMIS.2019.6.4.179
  11. B. Merrill, "Building Utility Decisions into Your Existing Behavior Tree," Game AI Pro: Collected Wisdom of Game AI Professionals, A K Peters/CRC Press, pp. 127-136, 2013.
  12. C.U. Lim, R. Baumgarten, and S. Colton, "Evolving behavior trees for the commercial game DEFCON," European Conference on the Application of Evolutionary Computations, pp. 100-110, 2010.
  13. R. Dey and C. Child, "QL-BT: Enhancing Behavior Tree Design and Implemtntation with Q-Learning," IEEE Conference on Computational Intelligence in Games, pp. 1-8, 2013.
  14. Kwon and J. Jang, "A Study on Implementation of Intelligent Character for MMORPG using Genetic Algorithm and Neural Networks," Journal of Korea Multimedia Society, Vol. 10, No. 5, pp. 631-641, 2007.
  15. Get started with Behavior Trees, https://gamedev-resources.com/get-started-with-behavior-trees (accessed December 12, 2021).