ISSN 2224-087X. Електроніка та інформаційні технології. 2018. Випуск 9. С. 113–119 Electronics and information technologies. 2018. Issue 9. P. 113–119 ___________________________ © Kushnir V., Koman B., 2018 УДК 519.172.1 CREATING AI FOR GAMES WITH UNREAL ENGINE 4 V. Kushnir, B. Koman Ivan Franko National University of Lviv, 50 Drahomanova St., Lviv, Ukraine, 79005 vasylll95@gmail.com Game AI in Unreal Engine 4 based on decision tree and called Behavior tree. The advantage of developing AI is the wide usage of this method in game industry for building an AI bots. It helps to build not a simple AI but a big model that helps us to build more interesting game. Nev- ertheless, this method of developing AI has a disadvantage which make hard to build a big system if you are only on a start to build AI with this method. In this paper I will show game engine called Unreal Engine 4 and how artificial intelligence can be developed. Also in this article will be shown a good start using this method for building great and large AI instantly. Key words: Unreal Engine 4, Behavior tree, decision tree, blackboard, selector, root, loop. Introduction [1]. Behavior tree is a graphical, modeling language and a good approach for developing big AI systems for games in a short period a time. It can be easily used to de- velop AI for different tasks. This method was developed by R.G. Dromey with first publication of some keyideasin 2001[1]. Early publications on this work used the terms "genetic software engineering" and "genetic design" to describe the application of behavior trees [1]. The reason for originally using the word genetic was because sets of genes, sets of jigsaw puzzle pieces and sets of requirements represented as behavior trees all appeared to share several key proper- ties: • they contained enough information as a set to allow them to be composed – with be- havior trees this allows a system to be built out of its requirements, • the order in which the pieces were put together was not important – with requirements this aids coping with complexity, • when all the members of the set were put together the resulting integrated entity ex- hibited a set of important properties. For behavior trees important emergent properties include: the integrated behavior of the system implied by the requirements and the coherent behavior of each component referred to in the requirements. Use of the term genetic came from eighteenth century by thinker Giambattista Vico, who said, "To understand something, and not merely be able to describe it, or analyse it into its component parts, is to understand how it came into being – its genesis, its growth true under- standing is always genetic". Despite these legitimate genetic parallels it was felt that this em- phasis led to confusion with the concept of genetic algorithms. As a result, the term behavior engineering [1] was introduced to describe the processes that exploit behavior trees to con- struct systems. The term "behavior engineering" has previously been used in a specialized area