Fully deterministic runs about dreamerv3 HOT 9 OPEN

Also, how many seeds were the non-Minecraft experiments run for?

from dreamerv3.

It's mean/std across seeds and at least 3 seeds per task, often more.

from dreamerv3.

Hi, are you asking for fully deterministic runs? I haven't paid much attention to this but I think the agent is already fully deterministic, so you'd probably just have to set the environment seed (make sure if you use more than 1 environment instance, that the environments have different seeds so they produce different data).

from dreamerv3.

Okay I will try that. Thank you for the quick response! What exactly is an "environment instance"? I couldn't find a clear definition in the paper.

from dreamerv3.

+1 on the question above. Maybe it's not that apparent in the paper, could you also provide some clarification on what the confidence intervals denote in the non-minecraft experiments (DMLab, DMC Proprio, Crafter, etc)? Is it std-error across multiple seeds, or std-error across a window of timesteps with a single seed, or something else?

from dreamerv3.

Update: I seeded dmc_control here. And still got non-deterministic runs. Are there other non-environment sources of randomness not seeded?

from dreamerv3.

I found some non-seeded randomness in the repo. Namely here and here. Wouldn't these affect the agent?

from dreamerv3.

I don't think those two methods are run ever. Could you check e.g. by adding asdf to the two methods to see if it errors?

from dreamerv3.

Seeding this it removes randomness from the first 1000 steps, but runs are non-deterministic afterwards.

from dreamerv3.