Skip to content

v0.4.9

Compare
Choose a tag to compare
@belerico belerico released this 01 Dec 14:49
· 87 commits to main since this release
52f49be

v0.4.9 Release Notes

  • Added torch>=2.0 as dependency in #161
  • Let mlflow be an optional package to be installed, i.e. the user can directly install it with pip install sheeprl[mlflow] in #164
  • Fix the resume_from_checkpoint in #163. In particular:
    • Added save_configs function to save the configs of the experiment in the <log_dir>/config.yaml file.
    • Fix the resume from checkpoint of all the algorithms (restart from the correct policy step + fix decoupled).
    • Given more flexibility to p2e finetuning scripts regarding the fabric configs.
    • MineDojo Wrapper: avoid modifying the kwargs (to always save consistent configs in the <log_dir>/config.yaml file).
    • Tensorboar Logger creation: update logger configs to always save consistent configs in the <log_dir>/config.yaml file.
    • Added as_dict() method (to dotdict class) to get a primitive python dictionary from a dotdict object.