第4局程序运行2542.5秒后出错, 错误信息为: Dst tensor is not initialized.
	 [[node save_3/RestoreV2 (defined at /home/inksci/deepolicy/deepfire-run/bf-nn3-0909-1945-1e-5-bs128-1217-gpu/battle-framework/agent/deepfire/lstm_policy.py:131) ]]

Original stack trace for 'save_3/RestoreV2':
  File "run_deepfire.py", line 171, in <module>
    main(env_id, num_episodes, speed)
  File "run_deepfire.py", line 155, in main
    results = dg_runner.run(num_episodes, speed)
  File "run_deepfire.py", line 88, in run
    self._run_agents(observation)           # 发送指令
  File "/home/inksci/deepolicy/deepfire-run/bf-nn3-0909-1945-1e-5-bs128-1217-gpu/battle-framework/env/env_runner.py", line 103, in _run_agents
    actions = agent.step(sim_time, obs_red, observation=observation)
  File "/home/inksci/deepolicy/deepfire-run/bf-nn3-0909-1945-1e-5-bs128-1217-gpu/battle-framework/agent/deepfire/deepfire_red.py", line 298, in step
    cmd = self.red_agent_deepfire.step(obs_red, observation, self.done, self.i_epsilon, sim_time)
  File "/home/inksci/deepolicy/deepfire-run/bf-nn3-0909-1945-1e-5-bs128-1217-gpu/battle-framework/agent/deepfire/lstm_policy.py", line 178, in step
    self.load_model()
  File "/home/inksci/deepolicy/deepfire-run/bf-nn3-0909-1945-1e-5-bs128-1217-gpu/battle-framework/agent/deepfire/lstm_policy.py", line 131, in load_model
    tf.train.Saver().restore(self.sess, checkpoint)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 825, in __init__
    self.build()
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 837, in build
    self._build(self._filename, build_save=True, build_restore=True)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 875, in _build
    build_restore=build_restore)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 508, in _build_internal
    restore_sequentially, reshape)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 328, in _AddRestoreOps
    restore_sequentially)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 575, in bulk_restore
    return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1696, in restore_v2
    name=name)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
    op_def=op_def)
  File "/home/inksci/miniconda3/envs/tf1gpu/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 2005, in __init__
    self._traceback = tf_stack.extract_stack()