async_dqn.py 文件源码

def deep_q_network():
    """ Architecture according to:
    http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html
    """
    @tt.model(tracker=tf.train.ExponentialMovingAverage(1 - .0005),    # TODO: replace with original weight freeze
                         optimizer=tf.train.RMSPropOptimizer(.00025, .95, .95, .01))
    def q_network(x):
        x /= 255
        x = layers.conv2d(x, 32, 8, 4)
        x = layers.conv2d(x, 64, 4, 2)
        x = layers.conv2d(x, 64, 3, 1)
        x = layers.flatten(x)
        x = layers.fully_connected(x, 512)
        x = layers.fully_connected(x, env.action_space.n, activation_fn=None)
        x = tf.identity(x, name='Q')
        return x

    return q_network