Developing a 2048 Player with Backward Temporal Coherence Learning and Restart
Developing a 2048 Player with Backward Temporal Coherence Learning and Restart
复制标题
开发具有后向时间一致性学习和重启功能的 2048 播放器
DOI：
10.1007/978-3-319-71649-7_15
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Kiminori Matsuzaki
中科院分区：
文献类型：
--
作者：
Kiminori Matsuzaki
益智游戏2048是在农业上玩的单人随机游戏。它在类似的滑动合并游戏中非常受欢迎。在游戏出现后，几位研究人员开发了基于n元组网络强化学习方法的2048年计算机玩家。正如论文标题所暗示的那样，由JaśKowski开发的最先进的播放器基于几种技术。在本文中，我们表明反向学习对2048年非常有用，因为游戏在一次游戏中有相当长的走法序列。我们还展示了一种重启策略，通过关注游戏的后期阶段来改善学习。与相同n元组网络的现有玩家相比，学习的玩家获得了更好的平均分数。
The puzzle game 2048 is a single-player stochastic game played on agrid. It is very popular among similar slide-and-merge games. After the appearance of the game, several researchers developed computer players for 2048 based on reinforcement learning methods withN-tuple networks. The state-of-the-art player developed by Jaśkowski is based on several techniques as the title of the paper implies. In this paper, we show that backward learning is very useful for 2048, since the game has quite a long sequence of moves in a single play. We also show a restart strategy to improve the learning by focusing on the later stage of the game. The learned player achieved better average scores than the existing players with the same set ofN-tuple networks.