dqn.py 文件源码

def __init__(self, n_actions):
        initializer = chainer.initializers.HeNormal()
        c1 = 32
        c2 = 64
        c3 = 64
        fc_unit = 256

        super(QFunction, self).__init__(
             # the size of the inputs to each layer will be inferred
            conv1=L.Convolution2D(4, c1, 8, stride=4, pad=0),
            conv2=L.Convolution2D(c1, c2, 4, stride=2, pad=0),
            conv3=L.Convolution2D(c2, c3, 3, stride=1, pad=0),
            #conv4=L.Convolution2D(64, c4, 3, stride=1, pad=1),
            fc1=L.Linear(3136, fc_unit, initialW=initializer),
            fc2=L.Linear(fc_unit, n_actions, initialW=initializer),
            #bnorm1=L.BatchNormalization(c1),
            #bnorm2=L.BatchNormalization(c2),
            #bnorm3=L.BatchNormalization(c3),
            #bnorm4=L.BatchNormalization(c4),
        )