ryanshea10

I don't think that I'm getting `'episode_done': True` as a result of two agents messaging simultaneously. I added some print statements to observe() in torch_agent.py and it seems like observe()...

Any thoughts on this? Let me know if there's any other information I can provide to clarify the problem.

Sure, here is the log file: [1658768422.865366.log](https://github.com/facebookresearch/ParlAI/files/9183334/1658768422.865366.log) And here is the stack trace: ``` World default had error RuntimeError('Last observe() was episode_done, but we never saw a corresponding self_observe to...

Does this clarify anything? Is there any other method I could use to clone the agent so that those sub modules are shared properly?

Just wanted to follow up on this issue again

Thanks for the response. That got rid of the error (I also had to change [these lines](https://github.com/facebookresearch/ParlAI/blob/982acb50f99261133ffa90ba04c569881389db6d/projects/blenderbot2/agents/sub_modules.py#L145-L146) though) however it seems to be causing some issues with the blenderbot personas/search...

I'm printing this in the worlds file whenever the world receives a message from the user. I tried reseting the model agent in the world before it observes/acts (inserting `self.model.reset()`...

I see, that is actually my current implementation. I wanted to see if calls could be done concurrently but it seems like getting that to work may be quite difficult....