We use cookies in order to improve the quality and usability of the HSE website. More information about the use of cookies is available here, and the regulations on processing personal data can be found here. By continuing to use the site, you hereby confirm that you have been informed of the use of cookies by the HSE website and agree with our rules for processing personal data. You may disable cookies in your browser settings.

  • A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Reinforcement Learning in Three-dimensional Visualization Environment

Student: Fedorova Anna

Supervisor:

Faculty: School of Computer Science, Physics and Technology

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2019

In a period of rapid development of artificial intelligence, there is a need to attract more and more people who are familiar with the field of reinforcement learning. Starting an autonomous introduction to this area could be difficult without specially prepared resources. Many of the existing platforms for experiments in reinforcement learning, however, provide weak visuals or require specialized skills in programming or deep knowledge in machine learning algorithms. Furthermore, many platforms lack the ability to flexibly configure the learning. In this paper, I describe the creation of a reinforcement learning framework based on the platform CoSpaces. The main goal of the work is the convenience of conducting experiments both for people new to the domain and for those who have deep knowledge in the field of reinforcement learning and want to test their own algorithms. The platform will give the opportunity to try different learning strategies, reinforcement learning tasks of various complexity, visualize the results achieved and explore the learning statistics. As a result, the framework allows a simple generation of new environments to solve, contains implementations of reinforcement learning algorithms, and provides an application programming interface for experimenting with new algorithms. In the next sections, the details of implementation will be described, as well as the specification of use cases.

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