Neural Network-Based Simulation of the Behavior Logic of a Bot in a Video Game

Student: Kashchenko Mikhail

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Computer Systems and Networks (Master)

Year of Graduation: 2019

In the current paper researched the dependence in the speed of training and the results of the game session of a computer game on the selected deep learning algorithms used to solve the problem of modeling the agent’s behavior taken incomplete information about the game world based on reinforcement learning, and on the delay time in the feedback on the reward received by the agent and from the selected frameskipping parameter. For the experiments, models of autonomous agents were developed and the model of the VizDoom environment was improved. The paper describes the results of the research and the technical implementation of the developed models. The thesis consists of 51 pages, 1 table, 15 illustrations, 39 sources were used.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses