Skip to content

Rename Generalization -> Environment Parameter Randomization #3646

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
Merged
merged 9 commits into from
Mar 18, 2020
Merged

Rename Generalization -> Environment Parameter Randomization #3646

merged 9 commits into from
Mar 18, 2020

Conversation

awjuliani
Copy link
Contributor

@awjuliani awjuliani commented Mar 17, 2020 •
edited
Loading

Proposed change(s)

  • Rename the "Generalization" feature to "Environment Parameter Randomization."
  • Replaces references to "reset parameters" with references to "environment parameters."

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

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

mmattar
mmattar reviewed Mar 18, 2020
View reviewed changes
@awjuliani awjuliani requested a review from andrewcoh March 18, 2020 18:58
@awjuliani awjuliani changed the title Rename Generalization -> Domain Variation Rename Generalization -> Environment Parameter Randomization Mar 18, 2020
ervteng
ervteng reviewed Mar 18, 2020
View reviewed changes
andrewcoh
andrewcoh reviewed Mar 18, 2020
View reviewed changes
andrewcoh
andrewcoh reviewed Mar 18, 2020
View reviewed changes
ervteng
ervteng approved these changes Mar 18, 2020
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.

LGTM

@andrewcoh
Copy link
Contributor

I didn't see domain randomization :'(

@awjuliani
Copy link
Contributor Author

I didn't see domain randomization :'(

Oops. Just added it.

andrewcoh
andrewcoh reviewed Mar 18, 2020
View reviewed changes
docs/Training-Environment-Parameter-Randomization.md
for training, the agent will be better suited to adapt (with higher performance)
to future unseen variations of the environment
To help agents robust and better generalizable to changes in the environment, the agent
can be trained over multiple variations of a given environment. We refer to this approach as **Environment Parameter Randomization**. For those familiar with Reinforcement Learning research, this approach is based on the concept of Domain Randomization (you can read more about it [here](https://arxiv.org/abs/1703.06907)). By using parameter randomization
Copy link
Contributor

Choose a reason for hiding this comment

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

👍

Copy link
Contributor Author

Choose a reason for hiding this comment

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

👍

@awjuliani awjuliani merged commit e8388b5 into master Mar 18, 2020
@delete-merged-branch delete-merged-branch bot deleted the develop-docs-domain-variations branch March 18, 2020 22:28
@github-actions github-actions bot locked as resolved and limited conversation to collaborators May 15, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers

@mmattar mmattar mmattar left review comments

@ervteng ervteng ervteng approved these changes

@andrewcoh andrewcoh andrewcoh approved these changes

@vincentpierre vincentpierre Awaiting requested review from vincentpierre

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@awjuliani @andrewcoh @mmattar @ervteng