Error when testing the sample command

[weiguowilliam]

When I run the sample command baselines weiguopro$ python -m baselines.run --alg=deepq --env=PongNoFrameskip-v4 --num_timesteps=1e6, it give me the RuntimeWarning and stuck there forever. I wonder what's reason here? What can I do? Thank you.

/Users/weiguopro/opt/miniconda3/envs/pomdp/lib/python3.6/site-packages/numpy/core/fromnumeric.py:3118: RuntimeWarning: Mean of empty slice.
  out=out, **kwargs)
/Users/weiguopro/opt/miniconda3/envs/pomdp/lib/python3.6/site-packages/numpy/core/_methods.py:85: RuntimeWarning: invalid value encountered in double_scalars
  ret = ret.dtype.type(ret / rcount)

I also tested with other arguments like python -m baselines.run --alg=ppo2 --env=BreakoutNoFrameskip-v4 --network=cnn --num_timesteps=1e7 --ent_coef=0.01 --num_env=8, it trained succefully.

Stepping environment...
Done.
---------------------------------------
| eplenmean               | 128       |
| eprewmean               | 0         |
| fps                     | 192       |
| loss/approxkl           | 0.000988  |
| loss/clipfrac           | 0.0732    |
| loss/policy_entropy     | 1.39      |
| loss/policy_loss        | -0.000406 |
| loss/value_loss         | 0.0259    |
| misc/explained_variance | -0.0654   |
| misc/nupdates           | 1         |
| misc/serial_timesteps   | 128       |
| misc/time_elapsed       | 5.33      |
| misc/total_timesteps    | 1.02e+03  |
---------------------------------------
Stepping environment...
Done.

...