Antonin RAFFIN
Antonin RAFFIN
>Seems like few-line change + docs for a seemingly obvious thing well, as always, I think we did not investigate that too much as MLP + Framestacking is usually both...
Well, you can always use SB2 DDPG without calling `mpirun` but then you will have to use only one environment. And A2C/PPO are meant to be fast whereas DDPG was...
> isn't added is because the original coders wanted the same writer to be accessible later, @hill-a could you comment on that?
Maybe related: https://github.com/hill-a/stable-baselines/issues/340 (try setting the entropy coeff to zero)
it seems your are using the same env 256 times... you should pass the env id.
Hello, Probably a duplicate of https://github.com/hill-a/stable-baselines/issues/196 Which OS are you using? I would recommend you to use PPO2 (or even [Stable-Baselines3](https://github.com/DLR-RM/stable-baselines3) PPO) as it also supports multiprocessing and usually give...
Hello, I have also encountered that issue in the past... I did not investigate a lot but I think I found that came from using multiple environments. Could you run...
>Not implemented yet, I will create a separete PR. Please do only one PR that solves this issue.
>Am I missing something? To me the only requirement to the timestep computation is that the values are plotted in the same order as they were computed. Looking at the...
@paolo-viceconte thanks, I'll try to take a look at what you did this week (unless @Miffyli can do it before), we have too many issue related to that function (cf...