Hi,

I am on a Ubuntu 18.4 and I created an env with conda create xx python=3.6

Then I directly run the install dependency script provided. And when I trying to run the python files in the created env, I encounter the following error:

python3 low_level_policy_main.py --option=changelane --evaluate --saved_policy_in_root Using TensorFlow backend. Traceback (most recent call last): File "low_level_policy_main.py", line 3, in from options.options_loader import OptionsGraph File "/home/chen/AutoD/wise-move-master/options/options_loader.py", line 4, in from backends import RLController, DDPGLearner, MCTSController, ManualPolicy File "/home/chen/AutoD/wise-move-master/backends/init.py", line 4, in from .kerasrl_learner import DDPGLearner, DQNLearner File "/home/chen/AutoD/wise-move-master/backends/kerasrl_learner.py", line 3, in from keras.models import Sequential, Model File "/home/chen/.local/lib/python3.6/site-packages/keras/init.py", line 3, in from . import utils File "/home/chen/.local/lib/python3.6/site-packages/keras/utils/init.py", line 6, in from . import conv_utils File "/home/chen/.local/lib/python3.6/site-packages/keras/utils/conv_utils.py", line 9, in from .. import backend as K File "/home/chen/.local/lib/python3.6/site-packages/keras/backend/init.py", line 1, in from .load_backend import epsilon File "/home/chen/.local/lib/python3.6/site-packages/keras/backend/load_backend.py", line 90, in from .tensorflow_backend import * File "/home/chen/.local/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 13, in from tensorflow.python.keras.utils import tf_utils File "/home/chen/.local/lib/python3.6/site-packages/tensorflow/python/keras/utils/tf_utils.py", line 23, in from tensorflow.python.framework import composite_tensor File "/home/chen/.local/lib/python3.6/site-packages/tensorflow/python/framework/composite_tensor.py", line 122, in pywrap_tensorflow.RegisterType("CompositeTensor", CompositeTensor) AttributeError: module 'tensorflow.python.pywrap_tensorflow' has no attribute 'RegisterType'

Thank you for your kindly help~