Junjia Liu

Well I just face the problem of 'AttributeError: 'FeedforwardGaussianPolicy' object has no attribute '_Serializable__initialize'', @avisingh599 . You might forget to answer this question. Could you give me some advice?

I tracked the codes and really did not find out where this attribute '_Serializable__initialize' is defined in gaussian_policy.py and base_policy.py.

Sorry to bother you. I found the solution. It's a problem caused by the wrong version of **serializable** package. Follow [this issue](https://github.com/rail-berkeley/softlearning/issues/107) to fix this bug.

Thank you very much for responding to me so quickly! And what you said is indeed the solution. Now I can run the code, but another mistake comes out. All...

I found that it is an error caused by ray.tune ``` /home/lab/anaconda3/envs/softlearning/lib/python3.6/site-packages/ray/tune/experiment.py(115)__init__()->None -> self.spec = spec (Pdb) r > /home/lab/anaconda3/envs/softlearning/lib/python3.6/site-packages/ray/tune/tune.py(200)run() -> checkpoint_dir = _find_checkpoint_dir(experiment) (Pdb) r 2019-12-18 21:24:28,480 INFO tune.py:64...

@hit618 Sorry, I couldn't fix it at the end. That might be a problem caused by the firewall and the incomplete install of the env.

Thanks for your reply. I have tried to modify the num_envs to 64/32/16, the error keeps the same

> https://github.com/NVIDIA-Omniverse/IsaacGymEnvs/blob/main/docs/rl_examples.md The above website says that Ant tasks can be trained using the SAC algorithm, but there is no specific modification of the configuration to AntSAC.yaml. What should I...

" RTX3090 , Isaac Gym - Preview 4 " got this error too.

## More suggestion Maybe you can find the installation path of your package automatically by these following codes ``` if elegantrl_path == "": if not hasattr(elegantrl, "__path__"): raise RuntimeError("elegantrl package...