Abstract
VCMI is a new, open-source project that could become one of the biggest testing platform for modern AI algorithms in the future. Its complex environment and turn-based gameplay make it a perfect system for any AI driven solution. It also has a large community of active players which improves the testability of target algorithms. This paper explores VCMI’s environment and tries to assess its complexity by providing a base solution for battle handling problem using two global optimization algorithms: Co-Evolution of Genetic Programming Trees and TD(1) algorithm with Back Propagation neural network. Both algorithms have been used in VCMI to evolve battle strategies through a fully autonomous learning process. Finally, the obtained strategies have been tested against existing solutions and compared with players’ best tactics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Vcmi documentation. http://wiki.vcmi.eu/index.php?title=Game_mechanics
Amato, C., Shani, G.: High-level reinforcement learning in strategy games. In: van der Hoek, W. et al. (ed.) AAMAS. pp. 75–82. IFAAMAS (2010)
Baier, H., Winands, M.: Monte-carlo tree search and minimax hybrids with heuristic evaluation functions. In: Cazenave, T., Winands, M., Björnsson, Y. (eds.) Computer Games, Communications in Computer and Information Science, vol. 504, pp. 45–63. Springer International Publishing, Berlin (2014)
Beal, D.: Learn from your opponent—but what if he/she/it knows less than you? In: Retschitzki, J., Haddab-Zubel, R. (eds.) Step by Step : Proceedings of the 4th Colloquium Board Games in Academia. pp. 123–132. Editions Universitaires (2002)
Björnsson, Y., Hafsteinsson, V., Jóhannsson, Á., Jónsson, E.: Efficient use of reinforcement learning in a computer game. In: Computer Games: Artificial Intellignece, Design and Education (CGAIDE’04), pp. 379–383 (2004)
Brafman, R.I., Tennenholtz, M.: R-MAX—a general polynomial time algorithm for near-optimal reinforcement learning. J. Mach. Learn. Res. 3, 213–231 (2002)
Browne, C., Powley, E.J., Whitehouse, D., Lucas, S.M., Cowling, P.I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., Colton, S.: A survey of monte carlo tree search methods. IEEE Trans. Comput. Intellig. AI Games 4(1), 1–43 (2012)
Conitzer, V., Sandholm, T.: Awesome: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. In: Fawcett, T., Mishra, N. (eds.) ICML. pp. 83–90. AAAI Press (2003)
Dreżewski, R., Siwik, L.: Multi-objective optimization using co-evolutionary multi-agent system with host-parasite mechanism. In: Alexandrov, V.N., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) Computational Science—ICCS 2006. LNCS, vol. 3993, pp. 871–878. Springer, Berlin (2006)
Dreżewski, R., Siwik, L.: Multi-objective optimization technique based on co-evolutionary interactions in multi-agent system. In: Giacobini, M., et al. (eds.) Applications of Evolutionary Computing, EvoWorkshops 2007. LNCS, vol. 4448, pp. 179–188. Springer, Berlin (2007)
Dreżewski, R., Siwik, L.: Agent-based co-operative co-evolutionary algorithm for multi-objective optimization. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing—ICAISC 2008. LNCS, vol. 5097, pp. 388–397. Springer, Berlin (2008)
Ekker, R.J.: Reinforcement Learning and Games. Master’s thesis, University of Groningen (2003)
Elidrisi, M., Johnson, N., Gini, M.: Fast learning against adaptive adversarial opponents. In: AAMAS’12: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (2012)
García-Martínez, C., Lozano, M.: Local search based on genetic algorithms. In: Siarry, P., Michalewicz, Z. (eds.) Advances in Metaheuristics for Hard Optimization. Natural Computing Series, pp. 199–221. Springer, Berlin (2008)
González-Pardo, A., Palero, F., Camacho, D.: Micro and macro lemmings simulations based on ants colonies. In: Esparcia-Alcázar, A.I., Mora, A.M. (eds.) Applications of Evolutionary Computation. Lecture Notes in Computer Science, pp. 337–348. Springer, Berlin (2014)
Jaskowski, W.: Algorithms for test-based problems. Ph.D. thesis, Institute of Computing Science, Poznan University of Technology, Poznan, Poland (2011)
Koza, J.R.: The genetic programming paradigm: genetically breeding populations of computer programs to solve problems. In: Soucek, B. (ed.) Dynamic, Genetic, and Chaotic Programming, pp. 203–321. Wiley, New York (1992)
Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the 11th International Conference on Machine Learning (ML-94), pp. 157–163. Morgan Kaufman, New Brunswick (1994)
Lucas, S., Samothrakis, S., Pérez, D.: Fast evolutionary adaptation for monte carlo tree search. In: Esparcia-Alcázar, A.I., Mora, A.M. (eds.) Applications of Evolutionary Computation. Lecture Notes in Computer Science, pp. 349–360. Springer, Berlin (2014)
McPartland, M., Gallagher, M.: Learning to be a bot: reinforcement learning in shooter games. In: Darken, C., Mateas, M. (eds.) AIIDE. The AAAI Press, Menlo Park (2008)
Nogueira, M., Cotta, C., Fernández-Leiva, A.J.: An analysis of hall-of-fame strategies in competitive coevolutionary algorithms for self-learning in RTS games. In: Nicosia, G., Pardalos, P.M. (eds.) LION. Lecture Notes in Computer Science, vol. 7997, pp. 174–188. Springer, Berlin (2013)
Perez, D., Rohlfshagen, P., Lucas, S.: Monte-carlo tree search for the physical travelling salesman problem. In: Di Chio, C., et al. (eds.) Applications of Evolutionary Computation. Lecture Notes in Computer Science, vol. 7248, pp. 255–264. Springer, Berlin (2012)
van der Ree, M., Wiering, M.: Reinforcement learning in the game of Othello: learning against a fixed opponent and learning from self-play. In: IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 2013, pp. 108–115 (2013)
Robilliard, D., Fonlupt, C., Teytaud, F.: Monte-carlo tree search for the game of “7 wonders”. In: Cazenave, T., Winands, M., Björnsson, Y. (eds.) Computer Games, Communications in Computer and Information Science, vol. 504, pp. 64–77. Springer International Publishing, Basel (2014)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Tanner, B., Sutton, R.S.: Td(lambda) networks: temporal-difference networks with eligibility traces. In: De Raedt, L., Wrobel, S. (eds.) ICML. ACM International Conference Proceeding Series, vol. 119, pp. 888–895. ACM (2005)
Uther, W., Veloso, M.: Adversarial reinforcement learning. Technical report. In: Proceedings of the AAAI Fall Symposium on Model Directed Autonomous Systems (1997)
Wender, S., Watson, I.: Using reinforcement learning for city site selection in the turn-based strategy game civilization iv. In: Hingston, P., Barone, L. (eds.) CIG. pp. 372–377. IEEE (2008)
Wiegand, P.R.: An analysis of cooperative coevolutionary algorithms. Ph.D. thesis, George Mason University (2003)
Acknowledgments
This research was partially supported by Polish Ministry of Science and Higher Education under AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications statutory project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wilisowski, Ł., Dreżewski, R. (2015). The Application of Co-evolutionary Genetic Programming and TD(1) Reinforcement Learning in Large-Scale Strategy Game VCMI. In: Jezic, G., Howlett, R., Jain, L. (eds) Agent and Multi-Agent Systems: Technologies and Applications. Smart Innovation, Systems and Technologies, vol 38. Springer, Cham. https://doi.org/10.1007/978-3-319-19728-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-19728-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19727-2
Online ISBN: 978-3-319-19728-9
eBook Packages: EngineeringEngineering (R0)