Parameterizing Artificial Intelligence Model for Control in Virtual Environments Based on Rinforcement Learning

Student: Fyodor Zakharov

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

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2024

This work is dedicated to the development of a customizable algorithm for managing game agents, combining reinforcement learning and a heuristic approach. The main goal is to create an artificial intelligence model that allows for setting tactics and behavior strategies for the agent. A neural network model based on the Soft Actor Critic reinforcement learning algorithm has been developed and trained in virtual environments simulating shooter video games. The research results allowed for evaluating the effectiveness of the proposed model compared to classical reinforcement learning algorithms and determining its potential in the field of managing the behavior of game agents.

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