[Feature Request] Tutorial of customizing environment

PKU-Alignment / omnisafe

JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

https://www.omnisafe.ai

Apache License 2.0

939 stars 132 forks source link

[Feature Request] Tutorial of customizing environment #291

Closed Gaiejj closed 3 months ago

Gaiejj commented 12 months ago

Required prerequisites

[X] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
[X] Consider asking first in a Discussion.

Motivation

OmniSafe currently has more issues and discussions involving the running of customized environments. We decided to provide a more detailed tutorial and examples of customized environments for users to understand OmniSafe's wrapper and adapter features. This tutorial is under development.

Solution

No response

Alternatives

No response

Additional context

No response

jyao97 commented 7 months ago

Hello, would you like to share any progress on this tutorial? Thanks a lot!

Gaiejj commented 7 months ago

We are currently in the iterative development process and expect to be ready within a week. Thank you very much for your support.

jyao97 commented 7 months ago

We are currently in the iterative development process and expect to be ready within a week. Thank you very much for your support.

Thank you! I look forward to reading it!

Gaiejj commented 7 months ago

@jyao97 Hello, We have released environment customization tutorials. Please feel free to use it and report any more problems. https://github.com/PKU-Alignment/omnisafe/tree/main/tutorials

Gaiejj commented 7 months ago

We will update the code library for the customized environment interface to PyPI recently. Before that, please choose to install from the source code when running the tutorial.

jyao97 commented 7 months ago

@jyao97 Hello, We have released environment customization tutorials. Please feel free to use it and report any more problems. https://github.com/PKU-Alignment/omnisafe/tree/main/tutorials

Thank you so much! Great work!

Gaiejj commented 6 months ago

We have released the new version of our project to PyPI, i.e., 0.5.0. However, if you running pip install omnisafe directly in colab, a warning will be raised:

WARNING: The following packages were previously imported in this runtime:
  [numpy]
You must restart the runtime in order to use newly installed versions.

Restarting will lose all runtime state, including local variables.

Simply rerun the colab page can resolve this issue.