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

Add reinforcement learning player #22

Open
wants to merge 46 commits into
base: master
Choose a base branch
from
Open

Add reinforcement learning player #22

wants to merge 46 commits into from

Commits on Sep 22, 2022

  1. Add RLlib to dependencies

    @klane
    klane committed Sep 22, 2022
    Configuration menu
    Copy the full SHA
    c06037c View commit details
    Browse the repository at this point in the history

Commits on Sep 23, 2022

  1. Add PyTorch to dependencies

    @klane
    klane committed Sep 23, 2022
    Configuration menu
    Copy the full SHA
    f8b56d6 View commit details
    Browse the repository at this point in the history

Commits on Sep 26, 2022

  1. Add TensorBoard to dependencies

    @klane
    klane committed Sep 26, 2022
    Configuration menu
    Copy the full SHA
    18e2ae4 View commit details
    Browse the repository at this point in the history

  2. Add function to get the index of a position

    @klane
    klane committed Sep 26, 2022
    Configuration menu
    Copy the full SHA
    0a376f9 View commit details
    Browse the repository at this point in the history

Commits on Sep 28, 2022

  1. Merge branch 'master' into rl-player

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    cefc2bb View commit details
    Browse the repository at this point in the history

  2. Add RL environment

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    ec7ca11 View commit details
    Browse the repository at this point in the history

  3. Add action mask model

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    f15640e View commit details
    Browse the repository at this point in the history

  4. Add self-play callback

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    e3e30ff View commit details
    Browse the repository at this point in the history

  5. Add random policy as initial self-play opponent

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    dfbbc9b View commit details
    Browse the repository at this point in the history

  6. Add __init__.py

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    8897a25 View commit details
    Browse the repository at this point in the history

  7. Add position index to invalid move error message

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    d37dfca View commit details
    Browse the repository at this point in the history

  8. Fix linting issues

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    33d1889 View commit details
    Browse the repository at this point in the history

  9. Update error message

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    eeb99af View commit details
    Browse the repository at this point in the history

  10. Add type hint

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    0da28a2 View commit details
    Browse the repository at this point in the history

  11. Add type hints for kwargs

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    b0e105a View commit details
    Browse the repository at this point in the history

  12. Simplify import statement

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    249143b View commit details
    Browse the repository at this point in the history

  13. Remove unnecessary pass

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    76aaf5d View commit details
    Browse the repository at this point in the history

  14. Comment unused code

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    3a532dc View commit details
    Browse the repository at this point in the history

  15. Change assert to instead raise exceptions

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    5145685 View commit details
    Browse the repository at this point in the history

  16. Check if there is no result

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    814216d View commit details
    Browse the repository at this point in the history

  17. Simplify done dictionary

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    8773d14 View commit details
    Browse the repository at this point in the history

  18. Check if no algorithm is provided

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    8bc2d38 View commit details
    Browse the repository at this point in the history

  19. Check if the episode is an exception

    @klane
    klane committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    09992d8 View commit details
    Browse the repository at this point in the history

Commits on Oct 2, 2022

  1. Add rolling win history to callback

    @klane
    klane committed Oct 2, 2022
    Configuration menu
    Copy the full SHA
    0cf23c5 View commit details
    Browse the repository at this point in the history

Commits on Oct 3, 2022

  1. Add callback to calculate win rates for all policies

    @klane
    klane committed Oct 3, 2022
    Configuration menu
    Copy the full SHA
    3c9a018 View commit details
    Browse the repository at this point in the history

  2. Add win rate calculator to generalize callbacks

    @klane
    klane committed Oct 3, 2022
    Configuration menu
    Copy the full SHA
    37d0680 View commit details
    Browse the repository at this point in the history

  3. Remove win rate callback

    @klane
    klane committed Oct 3, 2022
    Configuration menu
    Copy the full SHA
    44bb8e5 View commit details
    Browse the repository at this point in the history

  4. Unify policy ID formats 

    Renames main to main_0 and removes v from snapshot policies
    @klane
    klane committed Oct 3, 2022
    Configuration menu
    Copy the full SHA
    a84d7e2 View commit details
    Browse the repository at this point in the history

Commits on Oct 10, 2022

  1. Calculate game performance in callback

    @klane
    klane committed Oct 10, 2022
    Configuration menu
    Copy the full SHA
    19921f6 View commit details
    Browse the repository at this point in the history

  2. Add comments

    @klane
    klane committed Oct 10, 2022
    Configuration menu
    Copy the full SHA
    85ef6da View commit details
    Browse the repository at this point in the history

Commits on Oct 11, 2022

  1. Remove draw history from metrics

    @klane
    klane committed Oct 11, 2022
    Configuration menu
    Copy the full SHA
    5ad8e65 View commit details
    Browse the repository at this point in the history

Commits on Oct 12, 2022

  1. Ensure policy exceeds win rate against all opponents

    @klane
    klane committed Oct 12, 2022
    Configuration menu
    Copy the full SHA
    f9ecfdb View commit details
    Browse the repository at this point in the history

  2. Rename game attribute

    @klane
    klane committed Oct 12, 2022
    Configuration menu
    Copy the full SHA
    b053cfe View commit details
    Browse the repository at this point in the history

  3. Change observation method to accept a game object

    @klane
    klane committed Oct 12, 2022
    Configuration menu
    Copy the full SHA
    8a56e8c View commit details
    Browse the repository at this point in the history

  4. Sample observation space to initialize observation

    @klane
    klane committed Oct 12, 2022
    Configuration menu
    Copy the full SHA
    78281a3 View commit details
    Browse the repository at this point in the history

  5. Rename observation key

    @klane
    klane committed Oct 12, 2022
    Configuration menu
    Copy the full SHA
    f16e763 View commit details
    Browse the repository at this point in the history

Commits on Oct 14, 2022

  1. Remove unnecessary check 

    The game is over at this point and the result will not be None
    @klane
    klane committed Oct 14, 2022
    Configuration menu
    Copy the full SHA
    368d158 View commit details
    Browse the repository at this point in the history

  2. Do not create numpy array from observation batch 

    The observation is already a numpy array
    @klane
    klane committed Oct 14, 2022
    Configuration menu
    Copy the full SHA
    b3a3526 View commit details
    Browse the repository at this point in the history

  3. Store main policy as a local variable

    @klane
    klane committed Oct 14, 2022
    Configuration menu
    Copy the full SHA
    06a6202 View commit details
    Browse the repository at this point in the history

Commits on Oct 21, 2022

  1. Expand stat collection 

    - Calculate stats by batch, window, and overall
- Calculate win rate by opponent and color
- Calculate color balance
- Calculate windowed stats over one window instead of one per opponent
- Remove draw rate
    @klane
    klane committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    1af475f View commit details
    Browse the repository at this point in the history

Commits on Oct 23, 2022

  1. Remove win rates against opponents no longer playing

    @klane
    klane committed Oct 23, 2022
    Configuration menu
    Copy the full SHA
    48437c5 View commit details
    Browse the repository at this point in the history

  2. Use Color to set agent IDs

    @klane
    klane committed Oct 23, 2022
    Configuration menu
    Copy the full SHA
    63a408c View commit details
    Browse the repository at this point in the history

Commits on Oct 26, 2022

  1. Rename observation method

    @klane
    klane committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    dd9a6f1 View commit details
    Browse the repository at this point in the history

  2. Change percent method from static to a class method

    @klane
    klane committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    51c5e20 View commit details
    Browse the repository at this point in the history

Commits on Oct 30, 2022

  1. Change observation input from a game to a board

    @klane
    klane committed Oct 30, 2022
    Configuration menu
    Copy the full SHA
    38339a9 View commit details
    Browse the repository at this point in the history

Commits on Feb 26, 2023

  1. Bulk commit updates

    @klane
    klane committed Feb 26, 2023
    Configuration menu
    Copy the full SHA
    5a68f95 View commit details
    Browse the repository at this point in the history