Navigation

    蓝鲸ROS机器人论坛

    • Register
    • Login
    • Search
    • Categories
    • Tags
    • Popular
    ROS交流群
    ROS Group
    产品服务
    Product Service
    开源代码库
    Github
    官网
    Official website
    技术交流
    Technological exchanges
    激光雷达
    LIDAR
    ROS教程
    ROS Tourials
    深度学习
    Deep Learning
    机器视觉
    Computer Vision

    deepmind 在nature发布自学习AlphaGo Zero

    行业动态
    1
    1
    2535
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • frank
      frank last edited by frank

      谷歌旗下人工智能公司DeepMind宣布AlphaGo出现了升级版AlphaGoZero,证实无监督强化学习在围棋这类问题中有state of art 级别的有效性。AlphaGo打败李世石用了3000万盘比赛作为训练数据,而AlphaGo Zero仅用了490万盘比赛数据。经过3天的训练,AlphaGo Zero以100:0的战绩完胜AlphaGo。
      论文地址: https://deepmind.com/documents/119/agz_unformatted_nature.pdf
      官方博客: https://deepmind.com/blog/alphago-zero-learning-scratch

      1 Reply Last reply Reply Quote 0
      • 1 / 1
      • First post
        Last post
      Copyright © 2015-2023 BlueWhale community