dqn.py 文件源码

def dqn_test(env='OneRoundDeterministicReward-v0'):
    env = gym.make(env)
    env = ObservationShapeWrapper(env)

    @tt.model(tracker=tf.train.ExponentialMovingAverage(1-.01),
                         optimizer=tf.train.AdamOptimizer(.01))
    def q_network(x):
        x = layers.fully_connected(x, 32)
        x = layers.fully_connected(x, env.action_space.n, activation_fn=None,
                                                             weights_initializer=tf.random_normal_initializer(0, 1e-4))
        return x

    agent = DqnAgent(env, q_network, double_dqn=False, replay_start=100, annealing_time=100)

    rs = []
    for ep in range(10000):
        r, _ = agent.play_episode()

        rs.append(r)

        if ep % 100 == 0:
            print(f'Return after episode {ep} is {sum(rs)/len(rs)}')
            rs = []