nnet_cartpole_pg.py 文件源码

def build_network(name_scope, env):
    w_init_dense = tf.truncated_normal_initializer() #contrib.layers.xavier_initializer()
    b_init = tf.constant_initializer(value=0.0)

    with tf.variable_scope(name_scope):
        input_tensor = tf.placeholder(tf.float32,
                                      shape=tf_utils.get_input_tensor_shape(env),
                                      name='policy_input_'+name_scope)
        net = tf.contrib.layers.fully_connected(input_tensor,
                                                32, #env.action_space.n, #32,
                                                activation_fn=tf.nn.tanh, #sigmoid,
                                                weights_initializer=w_init_dense,
                                                biases_initializer=b_init,
                                                scope='dense1_'+name_scope)
        net = tf.contrib.layers.fully_connected(net,
                                                env.action_space.n,
                                                weights_initializer=w_init_dense,
                                                biases_initializer=b_init,
                                                scope='dense2_'+name_scope)
        net = tf.contrib.layers.softmax(net)

    return [input_tensor], [net]