restore model error about parl HOT 6 CLOSED

    def __init__(self, algorithm, obs_shape, act_dim,
                 learn_data_provider=None):
        assert isinstance(obs_shape, (list, tuple))
        self.obs_shape = obs_shape
        self.act_dim = act_dim
        # self.place = fluid.CUDAPlace(
        #     0) if machine_info.is_gpu_available() else fluid.CPUPlace()
        # self.fluid_executor = fluid.Executor(self.place)
        super(MPEAgent, self).__init__(algorithm)  
        if learn_data_provider:
            self.learn_reader.decorate_tensor_provider(learn_data_provider)
            self.learn_reader.start()

    def build_program(self):
        self.sample_program = fluid.Program()
        self.predict_program = fluid.Program()
        self.learn_program = fluid.Program()

        # fluid.layers.data()用来接收数据，类似placeholder
        with fluid.program_guard(self.sample_program):
            obs = layers.data(
                name='obs', shape=self.obs_shape, dtype='float32')
            self.sample_actions, self.behaviour_logits = self.alg.sample(obs)  # sample()

        # predict()
        with fluid.program_guard(self.predict_program):
            obs = layers.data(
                name='obs', shape=self.obs_shape, dtype='float32')
            self.predict_actions = self.alg.predict(obs)

        with fluid.program_guard(self.learn_program):
            obs = layers.data(
                name='obs', shape=self.obs_shape, dtype='float32')
            obs_act = layers.data(
                name='obs_act', shape=(-1, 21), dtype='float32')
            actions = layers.data(
                name='actions', shape=[], dtype='int64')
            behaviour_logits = layers.data(
                name='behaviour_logits', shape=[self.act_dim], dtype='float32')
            rewards = layers.data(
                name='rewards', shape=[], dtype='float32')
            dones = layers.data(
                name='dones', shape=[], dtype='float32')
            lr = layers.data(
                name='lr', shape=[1], dtype='float32', append_batch_size=False)
            entropy_coeff = layers.data(
                name='entropy_coeff', shape=[], dtype='float32')

            self.learn_reader = fluid.layers.create_py_reader_by_data(
                capacity=32,
                feed_list=[
                    obs, obs_act, actions, behaviour_logits, rewards, dones, lr, entropy_coeff
                ])

            obs, obs_act, actions, behaviour_logits, rewards, dones, lr, entropy_coeff = fluid.layers.read_file(
                self.learn_reader)
            vtrace_loss, kl = self.alg.learn(obs, obs_act, actions, behaviour_logits,
                                             rewards, dones, lr, entropy_coeff)
            self.learn_outputs = [
                vtrace_loss.total_loss, vtrace_loss.pi_loss,
                vtrace_loss.vf_loss, vtrace_loss.entropy, kl
            ]
        self.learn_program = parl.compile(self.learn_program,
                                          vtrace_loss.total_loss)

    def sample(self, obs_np):
        obs_np = obs_np.astype('float32')
        self.fluid_executor.run(fluid.default_startup_program())

        # FIXME: error
        sample_actions, behaviour_logits = self.fluid_executor.run(
            self.sample_program,
            feed={'obs': obs_np},
            fetch_list=[self.sample_actions, self.behaviour_logits])
        return sample_actions, behaviour_logits

    def predict(self, obs_np):
        obs_np = obs_np.astype('float32')
        # self.fluid_executor.run(fluid.default_startup_program())
        predict_actions = self.fluid_executor.run(
            self.predict_program,
            feed={'obs': obs_np},
            fetch_list=[self.predict_actions])[0]
        return predict_actions

    def learn(self):
        # self.fluid_executor.run(fluid.default_startup_program())
        total_loss, pi_loss, vf_loss, entropy, kl = self.fluid_executor.run(
            self.learn_program, fetch_list=self.learn_outputs)
        return total_loss, pi_loss, vf_loss, entropy, kl```

    agent.restore('./model.ckpt')
  File "/home/tianqi/anaconda3/lib/python3.6/site-packages/parl/core/fluid/agent.py", line 221, in restore
    filename=filename)
  File "/home/tianqi/anaconda3/lib/python3.6/site-packages/paddle/fluid/io.py", line 798, in load_params
    filename=filename)
  File "/home/tianqi/anaconda3/lib/python3.6/site-packages/paddle/fluid/io.py", line 675, in load_vars
    raise TypeError("program's type should be Program")
TypeError: program's type should be Program