Invalid Argument Error in epsize.

[smatsumori]

Caused by op 'deepq/epsize', defined at:
  File "train.py", line 78, in <module>
    main()
  File "train.py", line 62, in main
    model, actions, replay_buffer, explorer, learning_starts=10000
  File "/home/smatsumori/Workspace/nec/agent.py", line 47, in __init__
    grad_norm_clipping=10.0
  File "/home/smatsumori/Workspace/nec/build_graph.py", line 26, in build_train
    tf.int32, [num_actions], name='epsize'
  File "/home/smatsumori/.virtualenvs/tensorflow3/lib/python3.5/site-packages/tensorflow/python/ops/array_ops.py", line 1548, in placeholder
    return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
  File "/home/smatsumori/.virtualenvs/tensorflow3/lib/python3.5/site-packages/tensorflow/python/ops/gen_array_ops.py", line 2094, in _placeholder
    name=name)
  File "/home/smatsumori/.virtualenvs/tensorflow3/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
    op_def=op_def)
  File "/home/smatsumori/.virtualenvs/tensorflow3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/smatsumori/.virtualenvs/tensorflow3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1204, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'deepq/epsize' with dtype int32 and shape [3]
	 [[Node: deepq/epsize = Placeholder[dtype=DT_INT32, shape=[3], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
	 [[Node: deepq/Reshape/_171 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_712_deepq/Reshape", tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]