Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[🐛🔨 ] Fix sac target for continuous actions #5372

Merged
merged 3 commits into from May 19, 2021
Merged

[🐛🔨 ] Fix sac target for continuous actions #5372

merged 3 commits into from May 19, 2021

Conversation

vincentpierre
Copy link
Contributor

@vincentpierre vincentpierre commented May 17, 2021 •
edited

Proposed change(s)

Fixing the target entropy calculation for SAC in continuous and hybrid action cases.
Removing implicit broadcasting, changing the target entropy from -dim(A) ^ 2 to -dim(A)

Screen Shot 2021-05-18 at 09 33 08

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

Experiment doc

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

@vincentpierre vincentpierre self-assigned this May 17, 2021
ervteng
ervteng approved these changes May 19, 2021
View reviewed changes
Copy link
Contributor

@ervteng ervteng left a comment

Choose a reason for hiding this comment

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

👍

@vincentpierre vincentpierre merged commit 1c4ceaf into main May 19, 2021
@delete-merged-branch delete-merged-branch bot deleted the fix-sac-target branch May 19, 2021 05:20
@vincentpierre vincentpierre mentioned this pull request May 26, 2021
Merged
10 tasks
@github-actions github-actions bot locked as resolved and limited conversation to collaborators May 19, 2022
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers

@ervteng ervteng ervteng approved these changes

@andrewcoh andrewcoh Awaiting requested review from andrewcoh

Assignees

@vincentpierre vincentpierre

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
2 participants
@vincentpierre @ervteng