network.py 文件源码

def create_conv_model(self):
        # This is the place where neural network model initialized
        init = 'glorot_uniform'
        self.state_in = Input(self.state_dim)
        self.l1 = Convolution2D(32, 8, 8, activation='elu', init=init, subsample=(4, 4), border_mode='same')(
            self.state_in)
        self.l2 = Convolution2D(64, 4, 4, activation='elu', init=init, subsample=(2, 2), border_mode='same')(
            self.l1)
        # self.l3 = Convolution2D(64, 3, 3, activation='relu', init=init, subsample=(1, 1), border_mode='same')(
        #     self.l2)
        self.l3 = self.l2
        self.h = Flatten()(self.l3)
        self.hidden = Dense(256, init=init, activation='elu')(self.h)
        self.value = Dense(1, init=init)(self.hidden)
        self.policy = Dense(self.action_dim, init=init, activation='softmax')(self.hidden)
        self.q_values = self.entropy_coef * (Theano.log(self.policy + 1e-18) -
                                             Theano.tile(Theano.sum(Theano.log(self.policy + 1e-18) * self.policy,
                                                                    axis=[1], keepdims=True), (1, self.action_dim)))
        self.q_values = self.q_values + Theano.tile(self.value, (1, self.action_dim))
        self.model = Model(self.state_in, output=[self.policy, self.value])