標題: Multistage Temporal Difference Learning for 2048-Like Games
作者: Yeh, Kun-Hao
Wu, I-Chen
Hsueh, Chu-Hsuan
Chang, Chia-Chuan
Liang, Chao-Chin
Chiang, Han
資訊工程學系
Department of Computer Science
關鍵字: 2048;expectimax;stochastic puzzle game;temporal difference (TD) learning;threes
公開日期: 1-Dec-2017
摘要: Szubert and Jaskowski successfully used temporal difference (TD) learning together with n-tuple networks for playing the game 2048. However, we observed a phenomenon that the programs based on TD learning still hardly reach large tiles. In this paper, we propose multistage TD (MS-TD) learning, a kind of hierarchical reinforcement learning method, to effectively improve the performance for the rates of reaching large tiles, which are good metrics to analyze the strength of 2048 programs. Our experiments showed significant improvements over the one without using MS-TD learning. Namely, using 3-ply expectimax search, the program with MS-TD learning reached 32768-tiles with a rate of 18.31%, while the one with TD learning did not reach any. After further tuned, our 2048 program reached 32768-tiles with a rate of 31.75% in 10,000 games, and one among these games even reached a 65536-tiles, which is the first ever reaching a 65536-tiles to our knowledge. In addition, MS-TD learning method can be easily applied to other 2048-like games, such as Threes. Based on MS-TD learning, our experiments for Threes also demonstrated similar performance improvement, where the program with MS-TD learning reached 6144-tiles with a rate of 7.83%, while the one with TD learning only reached 0.45%.
URI: http://dx.doi.org/10.1109/TCIAIG.2016.2593710
http://hdl.handle.net/11536/144266
ISSN: 1943-068X
DOI: 10.1109/TCIAIG.2016.2593710
期刊: IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES
Volume: 9
起始頁: 369
結束頁: 380
Appears in Collections:Articles