烂柯围棋

标题: facebook围棋人工智能研究进展 [打印本页]

作者: 红色violin 时间: 2015-11-24 15:49
标题: facebook围棋人工智能研究进展
文章来源：弈楓圍棋天地

脸书（facebook ）围棋人工智能(AI)研究团队近日发表了一篇研究报告，不同于目前多数采取蒙地卡罗树搜寻演算法的电脑围棋软体，脸书围棋 AI 采取基于深度卷积神经网络(Deep Convolutional Neural Network)研究发展的型态比对技术(pattern-matching approach)，并以 "Darkforest" 之名在KGS围棋伺服器与其他电脑围棋软体(Go Bot) 、以及真人进行对弈，目前棋力大约1至2段，此外研究团队还提到如果同时结合两项技术，对局表现更佳，不过这与团队先前所宣称的目标尚有一大段距离，脸书谷哥两大网路巨擘相继投入资源研发围棋人工智能，期待有所重大突破。
原文：[attach]109[/attach]
Better Computer Go Player with Neural Network and Long-term PredictionYuandong Tian, Yan Zhu
(Submitted on 19 Nov 2015)

Competing with top human players in the ancient game of Go has been a long-term goal of artificial intelligence. Go's high branching factor makes traditional search techniques ineffective, even on leading-edge hardware, and Go's evaluation function could change drastically with one stone change. Recent works [Maddison et al. (2015); Clark & Storkey (2015)] show that search is not strictly necessary for machine Go players. A pure pattern-matching approach, based on a Deep Convolutional Neural Network (DCNN) that predicts the next move, can perform as well as Monte Carlo Tree Search (MCTS)-based open source Go engines such as Pachi [Baudis & Gailly (2012)] if its search budget is limited. We extend this idea in our bot named darkforest, which relies on a DCNN designed for long-term predictions. Darkforest substantially improves the win rate for pattern-matching approaches against MCTS-based approaches, even with looser search budgets. Against human players, darkforest achieves a stable 1d-2d level on KGS Go Server, estimated from free games against human players. This substantially improves the estimated rankings reported in Clark & Storkey (2015), where DCNN-based bots are estimated at 4k-5k level based on performance against other machine players. Adding MCTS to darkforest creates a much stronger player: with only 1000 rollouts, darkforest+MCTS beats pure darkforest 90% of the time; with 5000 rollouts, our best model plus MCTS beats Pachi with 10,000 rollouts 95.5% of the time.

Comments:	10 pages, 9 without references. Submission for ICLR 2016
Subjects:	Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:	arXiv:1511.06410 [cs.LG]
	(or arXiv:1511.06410v1 [cs.LG] for this version)

作者: 烂柯野人 时间: 2015-11-25 08:27
脸书谷哥两大网路巨擘相继投入资源研发围棋人工智能

欢迎光临烂柯围棋 (https://lanke.cc/forum/)