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.

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

[docs] Link to Imitation Learning docs in Readme, cleanup #3582

Merged
merged 7 commits into from
Mar 11, 2020

Conversation

ervteng
Copy link
Contributor

@ervteng ervteng commented Mar 6, 2020

Proposed change(s)

Link to the Imitation Learning docs in the Readme, and mention GAIL/BC as features. Also a bit of minor cleanup on the IL page.

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)

@ervteng ervteng requested a review from mmattar March 6, 2020 21:58
@@ -8,7 +8,7 @@ of training a medic NPC. Instead of indirectly training a medic with the help
of a reward function, we can give the medic real world examples of observations
from the game and actions from a game controller to guide the medic's behavior.
Imitation Learning uses pairs of observations and actions from
a demonstration to learn a policy. [Video Link](https://youtu.be/kpb8ZkMBFYs).
Copy link
Contributor Author

Choose a reason for hiding this comment

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

This video shows online BC, which isn't possible anymore given our current toolkit.

README.md Outdated
@@ -36,7 +36,7 @@ developer communities.
* Self-play mechanism for training agents in adversarial scenarios
* Train memory-enhanced agents using deep reinforcement learning
* Easily definable Curriculum Learning and Generalization scenarios
* Built-in support for Imitation Learning
* Built-in support for [Imitation Learning](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning
Copy link
Contributor

Choose a reason for hiding this comment

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

Not sure it is recommended to use the full URL. Maybe just do

Suggested change
* Built-in support for [Imitation Learning](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning
* Built-in support for [Imitation Learning](docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning

Copy link
Contributor Author

Choose a reason for hiding this comment

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

For the README it has to link to the latest_release files (and use the full path)... but you're right it was wrong. Updated.

@@ -85,3 +86,6 @@ inspector.
alt="BC Teacher Helper"
width="375" border="10" />
</p>

You can then specify the path to this file in your `trainer_config.yaml` file
when using BC or GAIL.
Copy link
Contributor

Choose a reason for hiding this comment

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

Maybe give the name of the argument?

behavioral_cloning:
        demo_path: <demo>

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Added examples for GAIL and BC

@@ -36,7 +36,7 @@ developer communities.
* Self-play mechanism for training agents in adversarial scenarios
* Train memory-enhanced agents using deep reinforcement learning
* Easily definable Curriculum Learning and Generalization scenarios
* Built-in support for Imitation Learning
* Built-in support for [Imitation Learning](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning
Copy link

Choose a reason for hiding this comment

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

why is it linking to latest_release? (similarly for PPO/SAC)

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I believe this was discussed at a prior meeting, but it's so users who hit the Readme.md page from Github will access the latest_release docs and not the master docs.

Copy link
Contributor

Choose a reason for hiding this comment

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

Yeah, that was the reason.

Copy link

Choose a reason for hiding this comment

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

The issue is that if we rename/move these files then it will result in broken links for older branches. Not a major issue, but calling it out.

@ervteng ervteng merged commit 84484b3 into master Mar 11, 2020
@delete-merged-branch delete-merged-branch bot deleted the develop-changereadmeIL branch March 11, 2020 20:27
@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.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants