论文标题
用于计算机的移动网络
Mobile Networks for Computer Go
论文作者
论文摘要
已证明，在深钢筋学习计划（例如Alpha Zero或一夫多妻制）中使用的神经网络的结构已显示出对由此产生的播放引擎的性能产生的很大影响。例如，使用剩余网络的使用使Alpha GO的强度增加了600个ELO。本文建议评估移动网络对使用监督学习的GO游戏的兴趣以及与Alpha Zero Heads不同的策略头和价值头的使用。评估了策略的准确性，值的均衡误差，具有参数数量的网络的效率，训练网络的播放速度和强度。
The architecture of the neural networks used in Deep Reinforcement Learning programs such as Alpha Zero or Polygames has been shown to have a great impact on the performances of the resulting playing engines. For example the use of residual networks gave a 600 ELO increase in the strength of Alpha Go. This paper proposes to evaluate the interest of Mobile Network for the game of Go using supervised learning as well as the use of a policy head and a value head different from the Alpha Zero heads. The accuracy of the policy, the mean squared error of the value, the efficiency of the networks with the number of parameters, the playing speed and strength of the trained networks are evaluated.
