File "/home/layaaa/my_projects/panda/safety_control/utils/mpi_tf.py", line 70, in compute_gradients buf = np.zeros(flat_grad.shape, np.float32) TypeError: __index__ returned non-int (type NoneType)

[khan008]

I got this error, how can I solved it. I am using tensorflow 1.13.1 and keras 2.2.4.

Traceback (most recent call last):
File "run_training.py", line 20, in
max_ep_len=500,
File "/home/siat/my_projects/robotic-arm-safeRL/safe_rl/pg/algos.py", line 13, in ppo
run_polopt_agent(agent=agent, **kwargs)
File "/home/siat/my_projects/robotic-arm-safeRL/safe_rl/pg/run_agent.py", line 215, in run_polopt_agent
train_pi = MpiAdamOptimizer(learning_rate=agent.pi_lr).minimize(pi_loss)
File "/home/layaaa/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 403, in minimize
grad_loss=grad_loss)
File "/home/layaaa/my_projects/panda/safety_control/utils/mpi_tf.py, line 70, in compute_gradients
buf = np.zeros(flat_grad.shape, np.float32)
TypeError: index returned non-int (type NoneType)