arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1604.07097cs.AI
收藏

Neurohex:一个深度Q学习的Hex Agent

Neurohex: A Deep Q-learning Hex Agent

University of Alberta(阿尔伯塔大学)

Kenny Young, Ryan Hayward, Gautham Vasan

摘要:

DeepMind最近在使用深度卷积神经网络和机器学习来构建超人级别的代理方面取得了巨大的成功-例如,通过深度Q学习为Atari游戏和通过强化学习为Go游戏-提出了许多问题,包括这些方法在其他领域将取得多大程度的成功。在本文中,我们考虑了Hex游戏的DQL:在监督初始化之后,我们使用selfplay来训练NeuroHex,这是一个11层的CNN,它在13 x13的棋盘上玩Hex。十六进制是经典的两个球员交替轮流石头放置游戏玩菱形的六边形细胞中的赢家是谁连接他们的两个对立的方面。尽管动作和状态空间很大,但我们的系统训练了一个能够在无需搜索的情况下进行强有力比赛的Q网络。经过两周的Q学习,NeuroHex作为第一名玩家和第二名玩家分别获得了20.4%和2.1%的胜率,对手是目前ICGA奥林匹克Hex冠军MoHex的1秒/移动版本。我们的数据表明,更多的训练时间可能会有进一步的改善。

英文摘要:

DeepMind's recent spectacular success in using deep convolutional neural nets and machine learning to build superhuman level agents --- e.g. for Atari games via deep Q-learning and for the game of Go via Reinforcement Learning --- raises many questions, including to what extent these methods will succeed in other domains. In this paper we consider DQL for the game of Hex: after supervised initialization, we use selfplay to train NeuroHex, an 11-layer CNN that plays Hex on the 13x13 board. Hex is the classic two-player alternate-turn stone placement game played on a rhombus of hexagonal cells in which the winner is whomever connects their two opposing sides. Despite the large action and state space, our system trains a Q-network capable of strong play with no search. After two weeks of Q-learning, NeuroHex achieves win-rates of 20.4% as first player and 2.1% as second player against a 1-second/move version of MoHex, the current ICGA Olympiad Hex champion. Our data suggests further improvement might be possible with more training time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑