Costa Huang

A new run https://wandb.ai/costa-huang/gym-microrts/runs/2v658xqx/logs?workspace=user-costa-huang seems successful, although the true skill evaluation is a bit buggy: see #41

This [run](https://wandb.ai/costa-huang/gym-microrts/runs/2v658xqx?workspace=user-costa-huang) successfully reproduced past best results. Closing the issue now. 

Now try reproducing the same results with `MicroRTSGridModeSharedMemVecEnv` from #34 in https://wandb.ai/gym-microrts/gym-microrts/runs/39stn3xh

Was able to reproduce same results with `MicroRTSGridModeSharedMemVecEnv`.  Also, SPS is about 10% faster! If we could make the NN faster, SPS will be even faster. 

The latest version only ships an interface similar to gym. See https://github.com/vwxyzjn/gym-microrts/blob/e4e11405a36044eab49d4cd2c2ed084b019bb999/hello_world.py#L10-L19

Oh @kachayev that's awesome! @BolunDai0216 is interested in working on this. Would you mind sharing your version here?

@kachayev thanks for sharing this! > I think that the use case of having API for 2 players would be much easier I agree. My first thought on this is...

Hi @timoklein, thanks for being interested in submitting a contribution! SAC discrete indeed sounds like an interesting addition to CleanRL. I just glanced at the paper and would recommend prototyping...

Hi @timoklein, thank you! The experiments look very interesting. > This implementation doesn't quite match the results of the paper which might be due to not using evaluation mode (i.e....

CC @braham-snyder we are tracking the progress w/ developing multi-objective hyperparameter optimization here. I think a first prototype is to support maximizing normalized scores while minimizing runtime. Let me know...