acme VS tonic

I'm tired of having my 200m frames of Atari take 5 days to run with dopamine, so I'm looking for another framework to use. I haven't been able to find one that's fast and hackable, preferably distributed or with vectorized environments. Anybody have suggestions? seed-rl seems promising but is archived (and in TF2). sample-factory seems super fast but to the best of my knowledge doesn't work with replay buffers. I've been trying to get acme working but documentation is sparse and many of the features are broken.

I'm training a few algorithms from Deepmind's acme library on some MuJoCo models and I'm wondering how long this will take to train and what it's going to do to my electric bill. Is a 3090 or two enough to train something to keep its balance, or do a task, or do I need to wait for the 8090 to come out?

Recently dm-acme also added support for multi-agent environments. Acme: https://github.com/deepmind/acme

Can anyone speak to their experience using acme (https://github.com/deepmind/acme) and by extension dm_env (https://github.com/deepmind/dm_env)? I'm wondering if it would be worthwhile for me to invest the time into converting my custom environment (which loosely follows the standard RL setup) over to this format.

acme/acme/agents/tf/mpo at master · deepmind/acme · GitHub

after installing it in a clean env, I tried to run the example provided for solving the gym cartpole env: https://github.com/deepmind/acme/blob/master/examples/control/run_d4pg_gym.py

Acme has a slightly different one: https://github.com/deepmind/acme which includes specs for agents, buffers etc. It is very general. You can see their component description here: https://github.com/deepmind/acme/blob/master/docs/components.md

I'm just finishing searching GitHub for the paper's link myself. I saw that link, but I'm working in Torch. I found this which is written in Torch, and has the MOMPO paper linked, but it's labelled as just a MPO.