Skip to content

Conversation

miguelalonsojr
Copy link
Contributor

Proposed change(s)

Fixes a bug where the critic is not normalized during training.

Useful links (Github issues, JIRA tickets, ML-Agents forum threads etc.)

#5583

Types of change(s)

  • Bug fix
  • New feature
  • Code refactor
  • Breaking change
  • Documentation update
  • Other (please describe)

Checklist

  • Added tests that prove my fix is effective or that my feature works
  • Updated the changelog (if applicable)
  • Updated the documentation (if applicable)
  • Updated the migration guide (if applicable)

Other comments

Copy link
Contributor

@maryamhonari maryamhonari left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! +1 on the test!

seed=seed,
param_manager=EnvironmentParameterManager(),
)
ppo_trainer = trainer_factory.generate(brain_name)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: these should be sac_trainers in this method

@miguelalonsojr miguelalonsojr merged commit cbc1993 into main Nov 2, 2021
@delete-merged-branch delete-merged-branch bot deleted the fix-critic-normalization-bug branch November 2, 2021 17:06
@github-actions github-actions bot locked as resolved and limited conversation to collaborators Nov 2, 2022
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants