首先感谢分享程序。
请问在6x6 四子棋的训练过程中，有没有调节learning_rate或者其他参数？
程序里的c_puct=5 , 温度t=1，学习率 0.002，batch_size 512 , deque最大长度10000, kl-targ=0.02 ,epochs=5
我使用你程序里的预设参数 tensorflow训练6x6 四子棋 ，loss下降到2左右就无法下降了，调节学习率也没成功。。。求帮助解答，谢谢

另外，不明白explain_var_old这个参考数值的意义。

During self-play phase we usually collect different examples for the same board states. Should we preprocess such examples before optimizing the NNet? In the current implementation, we don't preprocess them so we train NNet and expect different output from the same input values. I think this may be wrong.

Estimate bar should have text size comparable to scoring bar.

See index.css:

    #scoring {
        font-size: 1.6em;
    }
    #scoring button {
        font-size: 1.2em;
    }