Title: | 適用於小精靈的深度強化式學習之研究 A Study of Deep Reinforcement Learning for Ms. Pac-Man |
Authors: | 高黃江 吳毅成 Cao, Hoang Giang Wu, I-Chen 電機資訊國際學程 |
Keywords: | 深度強化式學習之;小精靈;深度類神經網路;Deep Reinforcement Learning;Ms. Pac-Man;Deep Neural Network |
Issue Date: | 2017 |
Abstract: | 深度類神經網路(Deep Neural Network)是2006年開始發展的一種機器學習技術。近年來,深度類神經網路被廣泛利用在資訊工程領域的各種應用上,並獲得出色的成績。 本論文將深度類神經網路應用在遊玩Ms. Pac-Man的遊戲上。深度加強學習(Deep Reinforcement Learning)是一種結合深度類神經網路與Q學習方法(Q-learning)的技術,也是加強學習的一個變體。此研究將Ms. Pac-Man遊戲中抽象化後的資訊當成類神經網路的輸入,使用其網路的人工智慧程式,可以在超過90%的嘗試中通過前兩個關卡。在最短通關時間與最佳通關分數兩項數據上,深度加強學習方法與之前的蒙地卡羅搜尋樹(Monte-Carlo Tree Search)方法相比,有顯著的進步。 Deep Neural Network (DNN), a branch of machine learning was introduced in 2006, have had remarkable success in of computer science. DNN can be applied to solving a wide range of problems. Deep Reinforcement Learning (DRL) is a combination of DNN and Q-learning, a form of Reinforcement Learning technique. This thesis applies DRL to create a program playing Ms. Pac-Man game. This study uses the abstracted information of Ms. Pac-Man game as the input of the network. Our program can pass the first level at a rate of 99.10%, the second at 91.20%, and the third at 82.60%. The performance of DRL method is significantly better than Monte Carlo Tree Search (MCTS) in terms of both time and score. |
URI: | http://etd.lib.nctu.edu.tw/cdrfb3/record/nctu/#GT070356166 http://hdl.handle.net/11536/140330 |
Appears in Collections: | Thesis |