8

我正在尝试加载tf-agents我保存的策略

try:
    PolicySaver(collect_policy).save(model_dir + 'collect_policy')
except TypeError:
    tf.saved_model.save(collect_policy, model_dir + 'collect_policy')

try/except 块的快速解释:最初创建策略时,我可以通过 保存它PolicySaver,但是当我再次加载它以进行另一次训练运行时,它是 a SavedModel,因此不能通过 保存PolicySaver

这似乎工作正常,但现在我想使用这个策略进行自我游戏,所以我self.policy = tf.saved_model.load(policy_path)在我的 AIPlayer 类中加载了这个策略。但是,当我尝试将其用于预测时,它不起作用。这是(测试)代码:

def decide(self, table):
    state = table.getState()
    timestep = ts.restart(np.array([table.getState()], dtype=np.float))
    prediction = self.policy.action(timestep)
    print(prediction)

table传递到函数中的包含游戏的状态,并且该函数ts.restart()是从我的自定义 pyEnvironment 中复制的,因此时间步的构造方式与在环境中的方式完全相同。但是,我收到以下错误消息prediction=self.policy.action(timestep)

ValueError: Could not find matching function to call loaded from the SavedModel. Got:
  Positional arguments (2 total):
    * TimeStep(step_type=<tf.Tensor 'time_step:0' shape=() dtype=int32>, reward=<tf.Tensor 'time_step_1:0' shape=() dtype=float32>, discount=<tf.Tensor 'time_step_2:0' shape=() dtype=float32>, observation=<tf.Tensor 'time_step_3:0' shape=(1, 79) dtype=float64>)
    * ()
  Keyword arguments: {}

Expected these arguments to match one of the following 2 option(s):

Option 1:
  Positional arguments (2 total):
    * TimeStep(step_type=TensorSpec(shape=(None,), dtype=tf.int32, name='time_step/step_type'), reward=TensorSpec(shape=(None,), dtype=tf.float32, name='time_step/reward'), discount=TensorSpec(shape=(None,), dtype=tf.float32, name='time_step/discount'), observation=TensorSpec(shape=(None,
79), dtype=tf.float64, name='time_step/observation'))
    * ()
  Keyword arguments: {}

Option 2:
  Positional arguments (2 total):
    * TimeStep(step_type=TensorSpec(shape=(None,), dtype=tf.int32, name='step_type'), reward=TensorSpec(shape=(None,), dtype=tf.float32, name='reward'), discount=TensorSpec(shape=(None,), dtype=tf.float32, name='discount'), observation=TensorSpec(shape=(None, 79), dtype=tf.float64, name='observation'))
    * ()
  Keyword arguments: {}

我究竟做错了什么?真的只是张量名称还是形状问题,我该如何改变它?

任何如何进一步调试的想法都值得赞赏。

4

1 回答 1

6

我通过手动构建 TimeStep 让它工作:

    step_type = tf.convert_to_tensor(
        [0], dtype=tf.int32, name='step_type')
    reward = tf.convert_to_tensor(
        [0], dtype=tf.float32, name='reward')
    discount = tf.convert_to_tensor(
        [1], dtype=tf.float32, name='discount')
    observations = tf.convert_to_tensor(
        [state], dtype=tf.float64, name='observations')
    timestep = ts.TimeStep(step_type, reward, discount, observations)
    prediction = self.policy.action(timestep)
于 2019-08-26T15:59:52.463 回答