Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

metaworld only works with gym 0.15.4

See original GitHub issue

gym version 0.15.5 upwards have deprecated the tags arguments in environment registration

They have specified the change here

Issue Analytics

State:
Created 4 years ago
Reactions:2
Comments:6 (2 by maintainers)

Top GitHub Comments

1reaction

ryanjuliancommented, Feb 14, 2020

Hi @iDurugkar

Thanks for filing this issue.

The metaworld API doesn’t make use of gym environment registration, so this should not affect functionality. Is it causing you to not be able to install metaworld?

We would happily accept a pull requests which simply deleted the contents of https://github.com/rlworkgroup/metaworld/blob/4528f84dab357d562824dac3edf159bc68399f23/metaworld/envs/mujoco/__init__.py

It’s not necessary for the benchmark to work and I think is the source of your problems.

0reactions

ryanjuliancommented, Apr 3, 2020

closed by #69

Top Results From Across the Web

garage/CHANGELOG.md at master - GitHub

A toolkit for reproducible reinforcement learning research. - garage/CHANGELOG.md at master · rlworkgroup/garage.

pip install gym==0.7.4 - PyPI

The OpenAI Gym: A toolkit for developing and comparing your reinforcement learning agents. ... and is compatible with any numerical computation library, ...

Error in importing environment OpenAI Gym - Stack Overflow

This worked for me via terminal: pip install gym[atari] pip install autorom[accept-rom-license]. After installing gym, it is 80 games.

How to Install OpenAI Gym in a Windows Environment

This command creates a Conda environment named “gym” that runs Python 3 and contains pip. If you don't install pip at the time...

Gym - :: Anaconda.org

The OpenAI Gym: A toolkit for developing and comparing your reinforcement learning agents. Conda · Files · Labels · Badges.