東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Game AI of Starcraft Ii Based on Dee...

Luo, Junjie,

Linked to FindBook

Google Book

Amazon

博客來

Game AI of Starcraft Ii Based on Deep Reinforment Learing /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Game AI of Starcraft Ii Based on Deep Reinforment Learing // Junjie Luo.
Author:	Luo, Junjie,
Description:	1 electronic resource (48 pages)
Notes:	Source: Masters Abstracts International, Volume: 84-12.
Contained By:	Masters Abstracts International84-12.
Subject:	Computer & video games. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30503138
ISBN:	9798379673789

Game AI of Starcraft Ii Based on Deep Reinforment Learing /
Luo, Junjie,

Game AI of Starcraft Ii Based on Deep Reinforment Learing /Junjie Luo. - 1 electronic resource (48 pages)

Source: Masters Abstracts International, Volume: 84-12.

The research problem of this article is the Game AI agent of StarCraft II based on Deep Reinforcement Learning (DRL). StarCraft II is viewed as the most challenging Real-time Strategy (RTS) game for now, and it is also the most popular game where researchers are developing and improving AI agents. Building AI agents of StarCraft II can help researchers on machine learning figure out the weakness of DRL and improve this series of algorithms. In 2018, DeepMind and Blizzard developed the StarCraft II Learning Environment (PySC2) to enable researchers to promote the development of AI agents. DeepMind started to develop a new project called AlphaStar after AlphaGo based on DRL, while several laboratories also published articles about the AI agents of StarCraft II. Most of them are researching on the AI agents of Terran and Zerg, which are two of three races in StarCraft II. AI agents show high-level performance compared with most StarCraft II players. However, the performance is far from defeating E-sport players because Game AI for StarCraft II has large observation space and large action space. However, there is no publication on Protoss, which is the remaining and most complicated race to deal with (larger action space, larger observation space) for AI agents due to its characteristics. Thus, in this paper, the research question is whether the AI agent of Protoss, which is developed by the model based on DRL, for a full-length game on a particular map can defeat the high-level built-in cheating AI. The population of this research design is the StarCraft II AI agents that researchers built based on their DRL models, while the sample is the Protoss AI agent in this paper. The raw data is from the game matches between the Protoss AI agent and built-in AI agents. PySC2 can capture features and numerical variables in each match to obtain the training data. The expected outcome is the model based on DRL, which can train a Protoss AI agent to defeat high-level game AI agents with the win rate. The model includes the action space of Protoss, the observation space and the realization of DRL algorithms. Meanwhile, the model is built on PySC2 v2.0, which provides additional action functions. Due to the complexity and the unique characteristics of Protoss in StarCraft II, the model cannot be applied to other games or platforms. However, how the model trains a Protoss AI agent can show the limitation of DRL and push DRL algorithm a little forward.

English

ISBN: 9798379673789Subjects--Topical Terms:

3548317
Computer & video games.

Game AI of Starcraft Ii Based on Deep Reinforment Learing /
LDR:03711nmm a22004093i 4500 001 2437050
005 20251119142629.5
006 m o d
007 cr|nu||||||||
008 261011s2020 miu||||||m |||||||eng d
020 $a 9798379673789
035 $a (MiAaPQD)AAI30503138
035 $a (MiAaPQD)Purdue12221960
035 $a AAI30503138
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Luo, Junjie, $e author. $3 3827922
245 1 0 $a Game AI of Starcraft Ii Based on Deep Reinforment Learing / $c Junjie Luo.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 1 electronic resource (48 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-12.
500 $a Advisors: Gusev, Dmitri.
502 $b M.Sc. $c Purdue University $d 2020.
520 $a The research problem of this article is the Game AI agent of StarCraft II based on Deep Reinforcement Learning (DRL). StarCraft II is viewed as the most challenging Real-time Strategy (RTS) game for now, and it is also the most popular game where researchers are developing and improving AI agents. Building AI agents of StarCraft II can help researchers on machine learning figure out the weakness of DRL and improve this series of algorithms. In 2018, DeepMind and Blizzard developed the StarCraft II Learning Environment (PySC2) to enable researchers to promote the development of AI agents. DeepMind started to develop a new project called AlphaStar after AlphaGo based on DRL, while several laboratories also published articles about the AI agents of StarCraft II. Most of them are researching on the AI agents of Terran and Zerg, which are two of three races in StarCraft II. AI agents show high-level performance compared with most StarCraft II players. However, the performance is far from defeating E-sport players because Game AI for StarCraft II has large observation space and large action space. However, there is no publication on Protoss, which is the remaining and most complicated race to deal with (larger action space, larger observation space) for AI agents due to its characteristics. Thus, in this paper, the research question is whether the AI agent of Protoss, which is developed by the model based on DRL, for a full-length game on a particular map can defeat the high-level built-in cheating AI. The population of this research design is the StarCraft II AI agents that researchers built based on their DRL models, while the sample is the Protoss AI agent in this paper. The raw data is from the game matches between the Protoss AI agent and built-in AI agents. PySC2 can capture features and numerical variables in each match to obtain the training data. The expected outcome is the model based on DRL, which can train a Protoss AI agent to defeat high-level game AI agents with the win rate. The model includes the action space of Protoss, the observation space and the realization of DRL algorithms. Meanwhile, the model is built on PySC2 v2.0, which provides additional action functions. Due to the complexity and the unique characteristics of Protoss in StarCraft II, the model cannot be applied to other games or platforms. However, how the model trains a Protoss AI agent can show the limitation of DRL and push DRL algorithm a little forward.
546 $a English
590 $a School code: 0183
650 4 $a Computer & video games. $3 3548317
650 4 $a Deep learning. $3 3554982
650 4 $a School environment. $3 541935
650 4 $a Neural networks. $3 677449
650 4 $a Libraries. $3 525303
650 4 $a Keyboards. $3 3681868
650 4 $a Linear algebra. $3 2923381
650 4 $a Skills. $3 3221615
650 4 $a Computer science. $3 523869
650 4 $a Educational administration. $3 2122799
650 4 $a Mathematics. $3 515831
650 4 $a Recreation. $3 535376
690 $a 0800
690 $a 0984
690 $a 0514
690 $a 0405
690 $a 0814
710 2 $a Purdue University. $e degree granting institution. $3 3759105
720 1 $a Gusev, Dmitri $e degree supervisor.
773 0 $t Masters Abstracts International $g 84-12.
790 $a 0183
791 $a M.Sc.
792 $a 2020
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30503138