Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.

Detalhes bibliográficos
Principais autores:	Mahmud, Aqil, Khan, Aswat Karim, Hasan Rafi, Mohammad Mehdi, Fahim, Kazi Rayhan
Outros Autores:	Rasel, Annajiat Alim
Formato:	Tese
Idioma:	English
Publicado em:	Brac University 2023
Assuntos:	Reinforcement learning Neural networks Games AI Proximal policy optimization Reinforcement learning.
Acesso em linha:	http://hdl.handle.net/10361/19954

id	10361-19954
record_format	dspace
spelling	10361-199542023-08-28T05:32:14Z Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games Mahmud, Aqil Khan, Aswat Karim Hasan Rafi, Mohammad Mehdi Fahim, Kazi Rayhan Rasel, Annajiat Alim Khan, Rubayat Ahmed Department of Computer Science and Engineering, Brac University Reinforcement learning Neural networks Games AI Proximal policy optimization Reinforcement learning. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023. Cataloged from PDF version of thesis. Includes bibliographical references (pages 23-24). This paper is intended to be a practical guide in terms of getting up and running with reinforcement learning. Ideally, it aims to bridge the gap between practi cal implementation and the theories available for RL. The theory of reinforcement learning involves two main components: an environment, which is the game itself and an agent, which performs an action based on its observation from the environ ment. Initially, no in-game rules will be given to the agent and it will be rewarded or punished based on the action that it will take. The goal is to increase Proximal Policy Optimization (PPO) to maximize the reward that our agent will get, so over time it will learn what action to take in order to do so. Therefore, we will develop an AI agent that will be able to learn how to play one of the most popular arcade games of all time, Street Fighter. We preprocess our game environment and apply hyperparameter tuning using PyTorch, Stable Baselines, and Optuna to do it. This approach will basically train different types of RL architecture and find a model with the most weighted parameters. Moreover, we are going to Fine Tune that model and run our test cases on it. We are going to see how a reinforcement learning algorithm learns to play. Aqil Mahmud Aswat Karim Khan Mohammad Mehdi Hasan Rafi Kazi Rayhan Fahim B. Computer Science and Engineering 2023-08-27T08:18:08Z 2023-08-27T08:18:08Z 2023 2023-01 Thesis ID: 18341010 ID: 18301282 ID: 18101629 ID: 18301114 http://hdl.handle.net/10361/19954 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 24 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Reinforcement learning Neural networks Games AI Proximal policy optimization Reinforcement learning.
spellingShingle	Reinforcement learning Neural networks Games AI Proximal policy optimization Reinforcement learning. Mahmud, Aqil Khan, Aswat Karim Hasan Rafi, Mohammad Mehdi Fahim, Kazi Rayhan Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.
author2	Rasel, Annajiat Alim
author_facet	Rasel, Annajiat Alim Mahmud, Aqil Khan, Aswat Karim Hasan Rafi, Mohammad Mehdi Fahim, Kazi Rayhan
format	Thesis
author	Mahmud, Aqil Khan, Aswat Karim Hasan Rafi, Mohammad Mehdi Fahim, Kazi Rayhan
author_sort	Mahmud, Aqil
title	Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games
title_short	Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games
title_full	Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games
title_fullStr	Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games
title_full_unstemmed	Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games
title_sort	implementation of reinforcement learning architecture to augment an ai that can self-learn to play video games
publisher	Brac University
publishDate	2023
url	http://hdl.handle.net/10361/19954
work_keys_str_mv	AT mahmudaqil implementationofreinforcementlearningarchitecturetoaugmentanaithatcanselflearntoplayvideogames AT khanaswatkarim implementationofreinforcementlearningarchitecturetoaugmentanaithatcanselflearntoplayvideogames AT hasanrafimohammadmehdi implementationofreinforcementlearningarchitecturetoaugmentanaithatcanselflearntoplayvideogames AT fahimkazirayhan implementationofreinforcementlearningarchitecturetoaugmentanaithatcanselflearntoplayvideogames
_version_	1814309064943861760

Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games

Registros relacionados