Chan

> @mamengyiyi > I also encountered this issue and what I do is to modify the code of ddpg_agent.py like below, > def act(self, obs, action_space): > action = action_space.sample()...

Hi, did you solve it @shuyanzhou

@Uehwan Thanks for youer all excellent work. have you finish updating this repo to python3

@jkulhanek Thank you for your reply. I try pytorch version1.1 and version1.3 in linux and python3.6.9. and there is no error or warning message. I uses the code from [load_state_dict](https://pytorch.org/tutorials/beginner/saving_loading_models.html)...

@jkulhanek I tried thread.run() to launch the program and succeeded. so I tried thsi program in torch 0.4.1 and the policy_network succeed in loading state_dict, but the program stopped at...

@jkulhanek it seems because of waiting pid # ThreadID: 140068893906688 File: "/usr/lib/python3.6/threading.py", line 884, in _bootstrap self._bootstrap_inner() File: "/usr/lib/python3.6/threading.py", line 916, in _bootstrap_inner self.run() File: "/home/usr/ws/visual-navigation-agent-pytorch/stacktracer.py", line 64, in run...

@jkulhanek When I release the code "mp.set_start_method("spawn"), the program ran, but it can not be stopped when I press ctr+c. And I think this operation may have negative impact on...

@jkulhanek any idea? please

> Thank you for your interest in our dataset. I hope to see great research results. > > The zip file just compressed the directory. Download something easy to download....

> Thank you for your interest. Not yet. The full dataset will be released in early June. We are in the process of the final annotation validation. We will notify...