請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71391完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 黃鐘揚(Chung-Yang (Ric) | |
| dc.contributor.author | Po-Cheng Chu | en |
| dc.contributor.author | 朱柏澂 | zh_TW |
| dc.date.accessioned | 2021-06-17T05:59:56Z | - |
| dc.date.available | 2024-02-19 | |
| dc.date.copyright | 2019-02-19 | |
| dc.date.issued | 2019 | |
| dc.date.submitted | 2019-02-13 | |
| dc.identifier.citation | REFERENCE
[1] P. Maratins, L. Custodio, R. Ventura. 2018. “A deep learning approach for understanding natural language commands for mobile service robots” arXiv preprint arXiv: 1807.03053. [2] Yagcioglu et al. 2018. “RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes”. In ACL, pages 1358–1368, Brussels, Belgium, October. ACL. [3] Graves et al. 2016. “Hybrid computing using a neural network with dynamic external memory”. Nature 538.7626 (2016): 471. [4] Vinyals et al. 2017, “StarCraft II: A New Challenge for Reinforcement Learning”. arXiv preprint arXiv:1708.04782. [5] A. Janusz, T. Tajmajer, and M. Swiechowski, 2017. “Helping AI to Play Hearthstone: AAIA’17 Data Mining Challenge”. In: M. Ganzha, L. Maciaszek, and M. Paprzycki, eds., Proceedings of the 2017 Federated Conference on Computer Science and Information Systems, vol. 11, 2017, 121–125, 10.15439/2017F573. [6] “HearthSim”. https://hearthsim.info/ [7] Ling et al. 2016. “Latent Predictor Networks for Code Generation”. In ACL, pages 599–609, Berlin, Germany, August. ACL. [8] Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2005. “BLEU: A method for automatic evaluation of machine translation” In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages 311–318. [9] Matthew Guzdial, Boyang Li, Mark O. Riedl. 2017. “Game Engine Learning from Video”. In International Joint Conference on Artificial Intelligence (IJCAI 2017). [10] Hochreiter, S. and Schmidhuber, J. 1997. Long short-term memory. Neural Computation, 9(8), 1735–1780 [11] Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. “GloVe: Global Vectors for Word Representation.”. Proceedings of the Empiricial Methods in Natural Language Processing (EMNLP 2014) 12. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71391 | - |
| dc.description.abstract | 將自然語言處理中，將文字敘述轉成操作指令是一個長期的挑戰，以探索此開放問題為目標，本篇論文關注一個含有大量操作性文字描述的電子卡牌遊戲：爐石戰記(Hearthstone)，並試圖理解卡牌上文字指示造成的狀態變化。
此文提出一套框架，利用觀察遊戲狀態(State)變化以及語意理解來建構環境。藉由模擬遊戲過程，產生大量遊戲狀態變化以及遊戲動作(Action)的對應關係，最終對未見過的卡牌上的操作性文字敘述進行行為預測。 | zh_TW |
| dc.description.abstract | In the field of natural language processing, transforming text commands into instructions for machines has always been a challenge. To explore this open problem, we focused on a well-known digital card game, Hearthstone, attempting to understand the card text descriptions and predict the resolved board states.
In this work we propose an approach to rebuild the environment model through rule text understanding and game state observing. By simulating the gameplay to produce state transition pairs after each card is played, this algorithm can predict fair amount of game states by reading rules from cards it has never seen before. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T05:59:56Z (GMT). No. of bitstreams: 1 ntu-108-R04921037-1.pdf: 1285630 bytes, checksum: 9fb918a64bcfa0224ab00f4ba7f4f1ce (MD5) Previous issue date: 2019 | en |
| dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vi LIST OF TABLES vii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Contributions of the Thesis 2 1.3 Organization of the Thesis 3 Chapter 2 Background 4 2.1 Game Engine Code Generation from Card Text 4 2.2 Game Engine Learning from Video 5 2.3 Winner Prediction from Game State 6 Chapter 3 Preliminaries 7 3.1 Basic Game Rule 7 3.2 Game State Definition 8 3.3 Game Actions 9 3.4 Long Short-Term Memory (LSTM) 11 Chapter 4 Game Rule Learning 13 4.1 Overview 13 4.2 Data Generation 14 4.2.1 Subset of Cards 14 4.2.2 Gameplay simulation 14 4.3 Model 15 4.3.1 Numerical Attributes 15 4.3.2 Card Description 16 4.3.3 Model Structure 16 4.4 Evaluation 17 Chapter 5 Experimental Results 18 5.1 Evaluation by Gameplay 23 5.1.1 Task 1: Plain Minions only 24 5.1.2 Task 2: Battlecry Minions only 24 Chapter 6 Conclusion and Future Work 25 REFERENCE 27 | |
| dc.language.iso | zh-TW | |
| dc.subject | 自然語意理解 | zh_TW |
| dc.subject | 自然語言處理 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 電腦對局 | zh_TW |
| dc.subject | 深度神經網路 | zh_TW |
| dc.subject | Natural Language Processing | en |
| dc.subject | Computer Gaming | en |
| dc.subject | Deep Neural Networks | en |
| dc.subject | Natural Language Understanding | en |
| dc.subject | Machine Learning | en |
| dc.title | 利用文意理解與觀察學習遊戲規則 | zh_TW |
| dc.title | Learning Game Rules by Observing and Text Understanding | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 107-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 于天立(Tian-Li Yu),周俊男 | |
| dc.subject.keyword | 自然語言處理,自然語意理解,深度神經網路,電腦對局,機器學習, | zh_TW |
| dc.subject.keyword | Natural Language Processing,Natural Language Understanding,Deep Neural Networks,Computer Gaming,Machine Learning, | en |
| dc.relation.page | 28 | |
| dc.identifier.doi | 10.6342/NTU201900394 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2019-02-13 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-108-1.pdf 未授權公開取用 | 1.26 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。