Kirill Lazarev

https://github.com/jcwleo/random-network-distillation-pytorch/blob/master/config.conf Is this config the last one to get similar results as on images above? I see last pull request is about normalization, maybe UseNorm = True improve reward_per_epi or...

Result by config in master branch. MontezumaRevengeNoFrameskip-v4 Right now, set NumEnv==128 and MaxStepPerEpisode==4500. I'll attach result when get 1200-2000 updates.

@jcwleo I see the difference in x-axis scale in reward_per_epi and reward_per_rollout plots. On your MontezumaRevengeNoFrameskip-v4 image they are 1.200k and 12.00k (10x scale). But on my temporary progress image...

Or the x-axis scale (global_update and sample_episode) depends on player survival/experience so on later updates x-axis scale will be the same?

@jcwleo Yes, correct. I have another small questions about code. How could be appropriate to ask? Every question as new issue, or move forward to ask in this issue?

NumEnv=128 and MaxStepPerEpisode==4500 Looks similar as in README. On NumEnv=128 I've stopped the process because swap is used.

I like that there are instructions for every language, but sometimes want to remove unnecessary information, maybe README file for each language with links or wiki could be a nice...

Hello. Not fast. Don't remember exactly, 1 or 2 NV 1080 Ti

It was 3 years ago. Could not help, I don't remember exactly what problem could cause.