Add EO1 policy support

[DelinQu]

What this does

• Introduced EO1 configuration and model classes, including EO1Config and EO1Policy.
• Updated pyproject.toml to include EO1 dependencies.
• Enhanced policy factory to support EO1.
• Added necessary imports and methods for EO1 functionality in existing files.
• Created README.md for EO1 policy documentation.

This commit establishes the foundation for the EO1 policy, enabling its integration into the existing framework.

This pull request adds support for a new policy type called "eo1" to the codebase. The changes introduce the configuration, registration, and factory logic for the new policy, as well as update dependency management and pre-commit exclusions to accommodate new files.

EO1 Policy Integration:

• Added a new configuration class EO1Config and a supporting EO1VisionFlowMatchingConfig in configuration_eo1.py, defining all relevant hyperparameters and validation logic for the EO1 policy.
• Registered EO1Config in the policy module’s __init__.py and the policy factory, enabling dynamic creation and use of EO1 policies via get_policy_class and make_policy_config. [1] [2] [3] [4]

Dependency and Build Updates:

• Added an eo1 extra in pyproject.toml with required dependencies, including flash-attn, and included it in the all extra for comprehensive installs. [1] [2]

Pre-commit Configuration:

• Updated .pre-commit-config.yaml to exclude the new EO1 modeling files from certain hooks to avoid formatting and typo checks during development.

Documentation:

• Added a placeholder README for the EO1 policy, linking to a shared documentation file.

How it was tested

Explain/show how you tested your changes.

Examples:

• Added test_something in tests/test_stuff.py.
• Added new_feature and checked that training converges with policy X on dataset/environment Y.
• Optimized some_function, it now runs X times faster than previously.

How to checkout & try? (for the reviewer)

Provide a simple way for the reviewer to try out your changes.

Examples:

pytest -sx tests/test_stuff.py::test_something

lerobot-train --some.option=true

SECTION TO REMOVE BEFORE SUBMITTING YOUR PR

Note: Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR. Try to avoid tagging more than 3 people.

Note: Before submitting this PR, please read the contributor guideline.