Advertisement

Multi-objective Adaptation of a Parameterized GVGAI Agent Towards Several Games

  • Ahmed KhalifaEmail author
  • Mike Preuss
  • Julian Togelius
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10173)

Abstract

This paper proposes a benchmark for multi-objective optimization based on video game playing. The challenge is to optimize an agent to perform well on several different games, where each objective score corresponds to the performance on a different game. The benchmark is inspired from the quest for general intelligence in the form of general game playing, and builds on the General Video Game AI (GVGAI) framework. As it is based on game-playing, this benchmark incorporates salient aspects of game-playing problems such as discontinuous feedback and a non-trivial amount of stochasticity. We argue that the proposed benchmark thus provides a different challenge from many other benchmarks for multi-objective optimization algorithms currently available. We also provide initial results on categorizing the space offered by this benchmark and applying a standard multi-objective optimization algorithm to it.

Keywords

Multi-objective optimization GVGAI MCTS 

References

  1. 1.
    Agapitos, A., Togelius, J., Lucas, S.M.: Multiobjective techniques for the use of state in genetic programming applied to simulated car racing. In: IEEE Congress on Evolutionary Computation, IEEE 2007, pp. 1562–1569 (2007)Google Scholar
  2. 2.
    Beume, N., Naujoks, B., Emmerich, M.: SMS-EMOA: multiobjective selection based on dominated hypervolume. Eur. J. Oper. Res. 181(3), 1653–1669 (2007). issn: 0377–2217CrossRefzbMATHGoogle Scholar
  3. 3.
    Bontrager, P., Khalifa, A., Mendes, A., Togelius, J.: Matching games, algorithms for general video game playing. In: AIIIDE (2016)Google Scholar
  4. 4.
    Bravi, I., Khalifa, A., Holmgård, C., Togelius, J.: Evolving UCT alternatives for general video game playing. In: The IJCAI-16 Workshop on General Game Playing, p. 63Google Scholar
  5. 5.
    Cazenave, T.: Evolving Monte Carlo tree search algorithms. Dept. Inf., Univ. Paris 8 (2007)Google Scholar
  6. 6.
    Chaslot, G.: Monte-Carlo tree search. Universiteit Maastricht (2010)Google Scholar
  7. 7.
    Ebner, M., Levine, J., Lucas, S.M., Schaul, T., Thompson, T., Togelius, J.: Towards a video game description language (2013)Google Scholar
  8. 8.
    Frydenberg, F., Andersen, K.R., Risi, S., Togelius, J.: Investigating MCTS modifications in general video game playing. In: Computational Intelligence and Games, pp. 107–113. IEEE (2015)Google Scholar
  9. 9.
    Gaina, R.D., Pérez-Liébana, D., Lucas, S.M.: General video game for 2 players: framework and competition. In: Proceedings of the IEEE Computer Science and Electronic Engineering Conference (CEEC) (2016)Google Scholar
  10. 10.
    Hingston, P.: Believable Bots. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Jacobsen, E.J., Greve, R., Togelius, J.: Monte Mario: platforming with MCTS. In: Proceedings of the Annual Conference on Genetic and Evolutionary Computation, pp. 293–300. ACM (2014)Google Scholar
  12. 12.
    Khalifa, A., Perez-Liebana, D., Lucas, S.M., Togelius, J.: General video game level generationGoogle Scholar
  13. 13.
    Mendes, A., Nealen, A., Togelius, J.: Hyperheuristic general video game playing. In: IEEE Computational Intelligence and Games (2016)Google Scholar
  14. 14.
    Ontanón, S., Synnaeve, G., Uriarte, A., Richoux, F., Churchill, D., Preuss, M.: A survey of real-time strategy game AI research and competition in starcraft. IEEE Trans. Comput. Intell. AI Games 5(4), 293–311 (2013)CrossRefGoogle Scholar
  15. 15.
    Perez, D., Samothrakis, S., Togelius, J., Schaul, T., Lucas, S., Couëtoux, A., Lee, J., Lim, C.-U., Thompson, T.: The 2014 general video game playing competition (2015)Google Scholar
  16. 16.
    Perez-Liebana, D., Samothrakis, S., Togelius, J., Lucas, S.M., Schaul, T.: General video game AI: competition, challenges and opportunities. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)Google Scholar
  17. 17.
    Pettit, J., Helmbold, D.: Evolutionary learning of policies for MCTS simulations. In: Proceedings of the International Conference on the Foundations of Digital Games, pp. 212–219. ACM (2012)Google Scholar
  18. 18.
    Preuss, M.: Adaptability of algorithms for real-valued optimization. In: Giacobini, M., et al. (eds.) Applications of Evolutionary Computing, pp. 665–674. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-01129-0 CrossRefGoogle Scholar
  19. 19.
    Renz, J.: AIBIRDS: the angry birds artificial intelligence competition. In: AAAI, pp. 4326–4327 (2015)Google Scholar
  20. 20.
    Soemers, D., Sironi, C.F., Schuster, T., Winands, M.H.M.: Enhancements for real-time Monte-Carlo tree search in general video game playing. In: Proceedings of the IEEE Conference on Computational Intelligence and Games (2016)Google Scholar
  21. 21.
    Togelius, J., Lucas, S.M., De Nardi, R.: Computational intelligence in racing games. In: Baba, N., Jain, L.C., Handa, H. (eds.) Advanced Intelligent Paradigms in Computer Games. Studies in Computational Intelligence, pp. 39–69. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-72705-7_3 CrossRefGoogle Scholar
  22. 22.
    Togelius, J., Preuss, M., Beume, N., Wessing, S., Hagelbäck, J., Yannakakis, G.N., Grappiolo, C.: Controllable procedural map generation via multiobjective evolution. Genet. Program Evolvable Mach. 14(2), 245–277 (2013)CrossRefGoogle Scholar
  23. 23.
    Togelius, J., Shaker, N., Karakovskiy, S., Yannakakis, G.N.: The Mario AI championship 2009–2012. AI Mag. 34(3), 89–92 (2013)Google Scholar
  24. 24.
    Tusar, T., Brockho, D., Hansen, N., Auger, A.: COCO: the bi-objective black box optimization benchmarking (bbob-biobj) test suite. In: CoRR abs/1604.00359 (2016)Google Scholar
  25. 25.
    Van Hoorn, N., Togelius, J., Wierstra, D., Schmidhuber, J.: Robust player imitation using multiobjective evolution. In: CEC, pp. 652–659. IEEE (2009)Google Scholar
  26. 26.
    Wessing, S.: Two-stage methods for multimodal optimization. Ph.D. thesis, TU Dortmund (2015).http://dx.doi.org/10.17877/DE290R-7804

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringNew York UniversityBrooklynUSA
  2. 2.Department of Information SystemsWestfälische Wilhelms-Universität MünsterMünsterGermany

Personalised recommendations