Skip to content

Conversation

Nitish89847
Copy link

This file registers a new custom environment 'MyCustomEnv'
so it can be recognized by the training framework and
visualized in RScope.

Steps included:

  1. Define the environment class with reset() and step() methods.
  2. Add it to the ALL_ENVS tuple in env_registry.
  3. Implement get_default_config(), load(), and get_domain_randomizer().
  4. Ensure Python uses the local _src folder (editable install recommended).
  5. Train using --env_name=MyCustomEnv and log_dir for RScope visualization.

- Fixed MyCustomEnv class to properly initialize with config
- Moved load(), get_default_config(), and get_domain_randomizer outside the class
- Consolidated test block into a single __main__ section
- Verified step(), reset(), and loader functionality
Copy link

google-cla bot commented Aug 15, 2025

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant