This paper deals with implementing Evolutionary Artificial Intelligence for MOBA Games that employs Genetic Algorithms to adjust and correct its own actions during the course of the game, becoming progressively better at gameplay over time. The typical operators of Genetic Algorithms such as Crossover and Mutation are used in a different sense. On the contrary to the traditional methodology of the Genetic Algorithms, Crossover and Mutations now may happen infrequently and without a definite sequential order. The individual in the population consists of the parameters necessary to drive the AI into the gameplay. The crossover points are the interactions of the AI with its allies in the game while the encounters with enemy AI serves as the Mutation points. Due to the nature of MOBA games, one may precede or succeed each other randomly and in real-time. The Genetic Algorithms hence defines an Evolutionary AI which is required for a typical MOBA or Action RTS game, thus making the AI capable of altering itself to better match the needs of the team, and also allowing the multi-reactive response of the enemy. Since Genetic Algorithms do not rewrite the entire AI behavior but only balance and optimize the parameters necessary for the actions taken by AI during the gameplay, it allows the AI to perform their duties in the game as deemed necessary by their characters' roles.

1. Eiben, A. E. et al (1994). "Genetic algorithms with multi-parent recombination". PPSN III: Proceedings of the International Conference on Evolutionary Computation. The Third Conference on Parallel Problem Solving from Nature: 78–87. ISBN 3-540-58484-6. .
2. Ting, Chuan-Kang (2005). "On the Mean Convergence Time of Multi-parent Genetic Algorithms Without Selection". Advances in Artificial Life: 403–412. ISBN 978-3-540-28848-0.
3. Feak, Steve; Steve Mescon (2009-03-19). "Postmortem: Defense of the Ancients". (http://web. archive. org/web/20101207055840/http://www. gamasutra. com/view/feature/3966/postmortem_defense_of_the_ancients. php)
4. Warcraft III Instruction Manual (World Editor ed. ). Blizzard Entertainment. 2002.
5. Perez, A. U. Multi-Reactive Planning for RTS Games. Universitat Autonoma de Bacelona
6. Walther, Anders. (2006). AI for Real Time Strategy Games – Development of AI for RTS Games capable of learning new strategies. IT – University of Copenhagen, Design, Communication and Media.

Multiplayer Online Battle Arena Moba Action-rts Dota Artificial Intelligence Genetic Algorithm Competitive