bdqn.py 文件源码

def test_dqn(env='Chain-v0'):
    import gym_mix
    env = gym.make(env)

    def pp(x):
        x = layers.fully_connected(x, 32)
        x = layers.fully_connected(x, 32)
        return x

    def head(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 = BootstrappedDQNAg(env, pp, head, replay_start=64)

    for ep in range(100000):
        R, _ = agent.play_episode()

        if ep % 100 == 0:
            print(f'Return after episode {ep} is {R}')