• David Hoeller's avatar
    Adds the Hydra configuration system for RL training (#700) · bf068c83
    David Hoeller authored
    # Description
    
    This MR adds utilities to enable the hydra configuration system.
    Using the `train.py` scripts, the user can now change any parameter in
    the environment or agent configs from command line inputs, for example:
    ``` 
    python source/standalone/workflows/rsl_rl/train.py --task Isaac-Cartpole-v0 --headless env.actions.joint_effort.scale=10.0
    ```
    
    ## Type of change
    
    - New feature (non-breaking change which adds functionality)
    
    ## Checklist
    
    - [ ] I have run the [`pre-commit` checks](https://pre-commit.com/) with
    `./isaaclab.sh --format`
    - [ ] I have made corresponding changes to the documentation
    - [ ] My changes generate no new warnings
    - [ ] I have added tests that prove my fix is effective or that my
    feature works
    - [ ] I have updated the changelog and the corresponding version in the
    extension's `config/extension.toml` file
    - [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
    exists there
    
    ---------
    Signed-off-by: 's avatarDavid Hoeller <dhoeller@nvidia.com>
    Co-authored-by: 's avatarMayank Mittal <12863862+Mayankm96@users.noreply.github.com>
    Co-authored-by: 's avatarKelly Guo <kellyg@nvidia.com>
    bf068c83
Name
Last commit
Last update
..
licenses Loading commit data...
source Loading commit data...
Makefile Loading commit data...
README.md Loading commit data...
conf.py Loading commit data...
index.rst Loading commit data...
make.bat Loading commit data...
requirements.txt Loading commit data...