Deep reinforcement learning for complex environment 1

This project delves into creating an Artificial Intelligence (AI) model tailored for the game Werewolf, focusing on strategic gameplay and realistic interaction. It aims to craft an AI by understanding and adapting to the intricate dynamics of the game and the nuances of player behaviour using deep...

Full description

Saved in:

Bibliographic Details
Main Author:	Goh, Peng Aik
Other Authors:	Bo An
Format:	Final Year Project
Language:	English
Published:	Nanyang Technological University 2024
Subjects:	Computer and Information Science
Online Access:	https://hdl.handle.net/10356/175205
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-175205
record_format	dspace
spelling	sg-ntu-dr.10356-1752052024-04-19T15:42:39Z Deep reinforcement learning for complex environment 1 Goh, Peng Aik Bo An School of Computer Science and Engineering boan@ntu.edu.sg Computer and Information Science This project delves into creating an Artificial Intelligence (AI) model tailored for the game Werewolf, focusing on strategic gameplay and realistic interaction. It aims to craft an AI by understanding and adapting to the intricate dynamics of the game and the nuances of player behaviour using deep reinforcement learning and large language models (LLMs). Through this, the project also aims to find out weaknesses in logic of LLMs and how these weaknesses can be alleviated with the aid of reinforcement learning and other means. Bachelor's degree 2024-04-19T13:40:31Z 2024-04-19T13:40:31Z 2024 Final Year Project (FYP) Goh, P. A. (2024). Deep reinforcement learning for complex environment 1. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175205 https://hdl.handle.net/10356/175205 en SCSE23-0059 application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Computer and Information Science
spellingShingle	Computer and Information Science Goh, Peng Aik Deep reinforcement learning for complex environment 1
description	This project delves into creating an Artificial Intelligence (AI) model tailored for the game Werewolf, focusing on strategic gameplay and realistic interaction. It aims to craft an AI by understanding and adapting to the intricate dynamics of the game and the nuances of player behaviour using deep reinforcement learning and large language models (LLMs). Through this, the project also aims to find out weaknesses in logic of LLMs and how these weaknesses can be alleviated with the aid of reinforcement learning and other means.
author2	Bo An
author_facet	Bo An Goh, Peng Aik
format	Final Year Project
author	Goh, Peng Aik
author_sort	Goh, Peng Aik
title	Deep reinforcement learning for complex environment 1
title_short	Deep reinforcement learning for complex environment 1
title_full	Deep reinforcement learning for complex environment 1
title_fullStr	Deep reinforcement learning for complex environment 1
title_full_unstemmed	Deep reinforcement learning for complex environment 1
title_sort	deep reinforcement learning for complex environment 1
publisher	Nanyang Technological University
publishDate	2024
url	https://hdl.handle.net/10356/175205
_version_	1806059763112345600

Deep reinforcement learning for complex environment 1

Similar Items