• ooctipus's avatar
    Updates SB3 ppo cfg so it trains under reasonable amount of time (#3726) · 6f013fb1
    ooctipus authored
    # Description
    
    This PR fixes the sb3_ppo_cfg for task Isaac-Ant-v0
    
    the parameter before had 4096 num_envs + horizon 512 + batch size 128 +
    n_epoch 20,
    that means the training one cycle it needs to for loop (20 * 512 * 4096)
    / 128 = 327680 times!
    
    which appears as if it is hanging forever
    
    the new config matches more closely with that of rl_games.
    
    I verified it will trains under 5 min 
    
    [Screencast from 2025-10-15
    13-56-21.webm](https://github.com/user-attachments/assets/2bc7bcd8-0063-46b9-adb0-67a6aa686732)
    
    ## Type of change
    
    <!-- As you go through the list, delete the ones that are not
    applicable. -->
    
    - Bug fix (non-breaking change which fixes an issue)
    
    ## Screenshots
    
    Please attach before and after screenshots of the change if applicable.
    
    <!--
    Example:
    
    | Before | After |
    | ------ | ----- |
    | _gif/png before_ | _gif/png after_ |
    
    To upload images to a PR -- simply drag and drop an image while in edit
    mode and it should upload the image directly. You can then paste that
    source into the above before/after sections.
    -->
    
    ## Checklist
    
    - [x] I have read and understood the [contribution
    guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
    - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
    `./isaaclab.sh --format`
    - [ ] I have made corresponding changes to the documentation
    - [x] 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
    - [x] I have added my name to the `CONTRIBUTORS.md` or my name already
    exists there
    
    <!--
    As you go through the checklist above, you can mark something as done by
    putting an x character in it
    
    For example,
    - [x] I have done this task
    - [ ] I have not done this task
    -->
    6f013fb1
Name
Last commit
Last update
.github Loading commit data...
.vscode Loading commit data...
apps Loading commit data...
docker Loading commit data...
docs Loading commit data...
scripts Loading commit data...
source Loading commit data...
tools Loading commit data...
.dockerignore Loading commit data...
.flake8 Loading commit data...
.gitattributes Loading commit data...
.gitignore Loading commit data...
.pre-commit-config.yaml Loading commit data...
CITATION.cff Loading commit data...
CONTRIBUTING.md Loading commit data...
CONTRIBUTORS.md Loading commit data...
LICENSE Loading commit data...
LICENSE-mimic Loading commit data...
README.md Loading commit data...
SECURITY.md Loading commit data...
VERSION Loading commit data...
environment.yml Loading commit data...
isaaclab.bat Loading commit data...
isaaclab.sh Loading commit data...
pyproject.toml Loading commit data...
pytest.ini Loading commit data...