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

[RLlib] Fix bugs in IMPALA/APPO + LSTM (new stack) and activate StatelessCartPole learning tests on new API stack. #47132

Merged
merged 11 commits into from
Aug 15, 2024
Merged

[RLlib] Fix bugs in IMPALA/APPO + LSTM (new stack) and activate StatelessCartPole learning tests on new API stack. #47132

merged 11 commits into from
Aug 15, 2024
+245 −105

Commits on Aug 14, 2024

  1. wip 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    2fe9a20 View commit details
    Browse the repository at this point in the history

  2. Learning stateless_cartpole_appo.py to 250.0 episode return in <500k ts. 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    2c8bbe9 View commit details
    Browse the repository at this point in the history

  3. Adding lower grad clip (20.0) to stabilize learning (still crashes so… 

    …metimes due to NaN weights).

Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    e4506b6 View commit details
    Browse the repository at this point in the history

  4. wip 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    3367076 View commit details
    Browse the repository at this point in the history

  5. Learns to >350.0 return in <700k ts. 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    5ea38ad View commit details
    Browse the repository at this point in the history

  6. wip 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    5c485fc View commit details
    Browse the repository at this point in the history

  7. Merge branch 'master' of https://github.com/ray-project/ray into acti… 

    …vate_appo_lstm_learning_tests
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    25ae410 View commit details
    Browse the repository at this point in the history

  8. wip 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    bd67533 View commit details
    Browse the repository at this point in the history

  9. wip 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    2282909 View commit details
    Browse the repository at this point in the history

Commits on Aug 15, 2024

  1. wip 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    9bb58f5 View commit details
    Browse the repository at this point in the history

  2. wip 

    Signed-off-by: sven1977 <[email protected]>
    @sven1977
    sven1977 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    2259230 View commit details
    Browse the repository at this point in the history