Adam Stelmaszczyk
Adam Stelmaszczyk
Please correct me if I'm wrong, but seems to me that default Django CSRF protection, if used correctly, prevents problems: https://docs.djangoproject.com/en/1.11/ref/csrf/ https://stormpath.com/blog/where-to-store-your-jwts-cookies-vs-html5-web-storage also says that: > Leveraging your web app...
@rwightman When I have a poor model, that falls from the starting point, then the OpenSim does the steps in less then a second. However, when the model is better,...
Free idea. Penalty for longer steps, reward shaping. So that the model prefers not to be stuck with legs deep in the ground.
> Oh, it has been updated -- thanks for spotting it. I'm not 100% sure what you are referring to, my feeling is that to `universe`. The universe [commit](https://github.com/openai/universe/commit/a4f78eb928ef2dc26247b16a75a4e862c2552f00) which...
It does, thanks a lot :) Because you mentioned that the original A3C work used Torch (which I didn't know) I googled more and found the [hyperparams](https://github.com/miyosuda/async_deep_reinforce/issues/1#issuecomment-214360003) they used. Also...
> You have to install all dependencies on host machine. After that, tmux is being used on your host so that all workers can run in parallel. All the instructions...
No change, since `savio` is True by [`--default`](https://github.com/pathak22/noreward-rl/blob/master/src/train.py#L136).
> which version of python is being called inside the tmux window? It will be Python from the host, since the `curiosity` virtualenv is not activated in tmux sessions. I...
Possibly related to #99.
Yes, please.