Kristian Hartikainen

Makes sense! I'll close this issue for now. Feel free open it up again if you think it's an issue in softlearning.

Ah, I see now. The problem probably happens when we save the sampler with `self._current_observation is not None` and then try to resume. In this case the environment would not...

Unfortunately I have not seen this error before. How did you install the environment? Are you on the latest master?

Yeah, could you try setting `mujoco-py==v1.50.1.0` and `gym=0.2.0` in the requirements.txt and try again? Note that you need to have mujoco 1.5 installed. Let me know how that goes!

The latest error seems like a version mismatch between `mujoco-py` and `gym` versions. Would you mind checking which version of `mujoco-py` those specific version of `gym` requires and then try...

Unfortunately we don't (yet) have any real robot examples available out-of-the-box. The main reason for this is that the real robot setup is quite heavily dependent on the hardware used...

I think what you're actually seeing is not the contents of `error.txt` but rather an error from bash. Can you wrap the `cat` argument in quotes? I.e.: ```bash cat "/home/acc12468eh/ray_results/dm_control/cheetah/run/2020-09-14T19-51-36-sl-sac/id=43fbb_00000-seed=8373_0_hidden_layer_sizes=(256,...

Hey @Maggern3, thanks for the question! Unfortunately, I don't have plans to implement the discrete version at least in the near future, mainly because I don't really work on discrete...

Noting myself that this is due to the change in tune's debug mode handling. A fix is to add `os.chdir(self.logdir)` in the beginning of the `ExperimentRunner` setup.

Hey @kapsl, Yeah, the trials should automatically be parallelized locally if you run `softlearning run_example_local` and set the resources correctly. By correct, I mean that, for example, if your computer...