Skip to content

Documentation for Goal conditioning#5149

Merged
vincentpierre merged 12 commits into
mainfrom
goal-conditioning-docs
Mar 29, 2021
Merged

Documentation for Goal conditioning#5149
vincentpierre merged 12 commits into
mainfrom
goal-conditioning-docs

Conversation

@vincentpierre

Copy link
Copy Markdown
Contributor

Proposed change(s)

Documentation for Goal conditioning

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

@vincentpierre vincentpierre self-assigned this Mar 17, 2021
@vincentpierre vincentpierre marked this pull request as ready for review March 18, 2021 19:23
@vincentpierre vincentpierre requested a review from awjuliani March 18, 2021 19:23
Comment thread docs/Training-Configuration-File.md Outdated
Comment thread docs/Learning-Environment-Design-Agents.md Outdated

It is possible for agents to collect observations that will be treated as "goal".
A goal is used to condition the policy of the Agent, meaning that if the goal
changes, the behavior of the Agent will change as well. Note that this is true

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

I think we should say that goals change the policy, which is a mapping from (observation -> action)

@awjuliani awjuliani left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Do we want to refer to it as a "goal signal" instead of a goal?


### Goal Signals

It is possible for agents to collect observations that will be treated as "goal."

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Suggested change
It is possible for agents to collect observations that will be treated as "goal."
It is possible for agents to collect observations that will be treated as a "goal."

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

I think within this paragraph we should also call these goal signals, and not goals.

Comment thread docs/Learning-Environment-Design-Agents.md Outdated
Co-authored-by: Ervin T. <ervin@unity3d.com>
Comment thread docs/Learning-Environment-Design-Agents.md Outdated
Comment thread docs/Learning-Environment-Design-Agents.md Outdated
Comment thread docs/Learning-Environment-Design-Agents.md Outdated
Comment thread docs/Learning-Environment-Design-Agents.md Outdated
Comment thread docs/Learning-Environment-Design-Agents.md Outdated
@vincentpierre vincentpierre merged commit 96a5aaf into main Mar 29, 2021
@delete-merged-branch delete-merged-branch Bot deleted the goal-conditioning-docs branch March 29, 2021 18:58
@github-actions github-actions Bot locked as resolved and limited conversation to collaborators Mar 29, 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.

3 participants