Exploration of Complex Environments in Reinforcement Learning

Student: Sokolov Roman

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2020

Reinforcement learning algorithms often face complex environments with extremely rare rewards and complicated transition dynamics between states. In such situation effective environment exploration is a key factor affecting agent training. One of possible solution is building a special dense and informative reward function. In this paper we introduce and study new intrinsic motivation algorithms based on agent memory. The purpose of these algorithms is to assist the agent in exploring a complex environment to search for these rare external rewards.

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