How long did you get 6100?

[zhr211]

Hello,

I also built RND model, but I am stuck at 2500... How many total steps will agent improve further? I am not sure whether it is related to bug of my code, so I wanna check with you. Thank you.

[jcwleo]

My model got 6100 when it run 16k rollout. :)

[zhr211]

omg....i broke out 2500, but already 1500 episode, still stay at 2900

[jcwleo]

how many env did you use? I used 128 env

[zhr211]

I also used 128...TOT....

[jcwleo]

It was also mentioned in the paper that performance was not very good. Why don't you learn more? Reinforcement learning is always a battle of patience. :)

[zhr211]

lol.....everyday morning, I just turn on the computer with great anticipation

[alivarastepour]

@jcwleo How many GBs of RAM does a run with 128 envs need?

[jcwleo]

@alivarastepour I don't remember exactly now. I think it would be good to modify the config file and experiment with it. It did not require more ram capacity than expected.