arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.03467cs.AI
收藏

计算机围棋的改进模型与探索

Improving Model and Search for Computer Go

LAMSADE Université Paris-Dauphine, PSL, CNRS(巴黎第九大学LAMSADE实验室,PSL研究大学,国家科学研究中心)

Tristan Cazenave

摘要:

游戏中深度强化学习的标准是使用残差网络,并增加网络的深度以获得更好的结果。我们建议改进移动网络作为替代残留的网络和实验显示的播放强度的网络,根据其宽度和深度。我们还提出了一个推广的PUCT搜索算法,改进了PUCT。

英文摘要:

The standard for Deep Reinforcement Learning in games, following Alpha Zero, is to use residual networks and to increase the depth of the network to get better results. We propose to improve mobile networks as an alternative to residual networks and experimentally show the playing strength of the networks according to both their width and their depth. We also propose a generalization of the PUCT search algorithm that improves on PUCT.

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。

↑