gym VS acme

A co-founder announced they disbanded their robots team a couple years ago: https://venturebeat.com/business/openai-disbands-its-robotic...

That was the same time they depreciated OpenAI Gym: https://github.com/openai/gym

This includes single-agent Gymnasium wrappers for DM Control, DM Lab, Behavior Suite, Arcade Learning Environment, OpenAI Gym V21 & V26. Multi-agent PettingZoo wrappers support DM Control Soccer, OpenSpiel and Melting Pot. For more information, read the release notes here:

When I browse fetch_env.py, I have a question about the following code snippet:

Nvm, this works for me '!pip install setuptools==65.5.0' Source: https://github.com/openai/gym/issues/3176

how would this interact/compare with https://github.com/openai/gym?

If you'd like to learn more about reinforcement learning or play with a number of samples in controlled environments, I highly recommend you look at the documentation for OpenAI's Gym library and particularly the basic usage page. OpenAI's Gym provides a standardized environment for performing reinforcement learning on classic Atari games and a few other platforms and should be an educational resource. If you'd like a more detailed example, check out this tutorial on Paperspace's blog.

Frozen Lake is an OpenAI Gym environment in which an agent is rewarded for traversing a frozen surface from a start position to a goal position without falling through any perilous holes in the ice.

typically a more relaxed approach is taken via reinforcement learning, but it requires that you can simulate the game via a given gamestate. take a look at e.g. https://www.gymlibrary.dev/

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