Skip to content

[RLlib] Behavioral Cloning (from MARWIL).#10619

Merged
sven1977 merged 18 commits intoray-project:masterfrom
sven1977:behavioral_cloning
Sep 9, 2020
Merged

[RLlib] Behavioral Cloning (from MARWIL).#10619
sven1977 merged 18 commits intoray-project:masterfrom
sven1977:behavioral_cloning

Conversation

@sven1977
Copy link
Copy Markdown
Contributor

@sven1977 sven1977 commented Sep 7, 2020

This PR adds a BCTrainer, simply derived from the MARWIL algo by force-setting beta to 0.0.
Background: Users asked for this algo specifically (and cannot find it in the repo).

Why are these changes needed?

Related issue number

Checks

  • I've run scripts/format.sh to lint the changes in this PR.
  • I've included any doc changes needed for https://docs.ray.io/en/latest/.
  • I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failure rates at https://ray-travis-tracker.herokuapp.com/.
  • Testing Strategy
    • Unit tests
    • Release tests
    • This PR is not tested (please justify below)

@sven1977 sven1977 requested a review from ericl September 7, 2020 10:21
@ericl
Copy link
Copy Markdown
Contributor

ericl commented Sep 9, 2020

Also add it to the documentation?

@sven1977 sven1977 merged commit 4b278c3 into ray-project:master Sep 9, 2020
@sven1977 sven1977 deleted the behavioral_cloning branch March 27, 2021 11:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants