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

[WIP] MDQN #74

Open
wants to merge 16 commits into
base: master
Choose a base branch
from
Open

[WIP] MDQN #74

wants to merge 16 commits into from

Commits on Jul 30, 2020

  1. add MDQN agent and example script

    @marioyc
    marioyc committed Jul 30, 2020
    Configuration menu
    Copy the full SHA
    b8689ac View commit details
    Browse the repository at this point in the history

  2. cast to long

    @marioyc
    marioyc committed Jul 30, 2020
    Configuration menu
    Copy the full SHA
    73f5e98 View commit details
    Browse the repository at this point in the history

Commits on Jul 31, 2020

  1. add scaling and clipping

    @marioyc
    marioyc committed Jul 31, 2020
    Configuration menu
    Copy the full SHA
    87c298c View commit details
    Browse the repository at this point in the history

  2. add tensor device

    marioyc committed Jul 31, 2020
    Configuration menu
    Copy the full SHA
    64d4742 View commit details
    Browse the repository at this point in the history

  3. add reference

    @marioyc
    marioyc committed Jul 31, 2020
    Configuration menu
    Copy the full SHA
    f33dfa5 View commit details
    Browse the repository at this point in the history

  4. fix scaled log policy bonus

    @marioyc
    marioyc committed Jul 31, 2020
    Configuration menu
    Copy the full SHA
    b72db9a View commit details
    Browse the repository at this point in the history

Commits on Aug 3, 2020

  1. change default target update interval according to the paper

    @marioyc
    marioyc committed Aug 3, 2020
    Configuration menu
    Copy the full SHA
    c73de3e View commit details
    Browse the repository at this point in the history

  2. fix log-sum-exp-trick calculation

    @marioyc
    marioyc committed Aug 3, 2020
    Configuration menu
    Copy the full SHA
    0c46d76 View commit details
    Browse the repository at this point in the history

  3. fix next value calculation, add logs

    @marioyc
    marioyc committed Aug 3, 2020
    Configuration menu
    Copy the full SHA
    327d60d View commit details
    Browse the repository at this point in the history

Commits on Aug 4, 2020

  1. add additional statistics

    @marioyc
    marioyc committed Aug 4, 2020
    Configuration menu
    Copy the full SHA
    bfdcae0 View commit details
    Browse the repository at this point in the history

  2. fix debug of pi's sum

    @marioyc
    marioyc committed Aug 4, 2020
    Configuration menu
    Copy the full SHA
    eac093c View commit details
    Browse the repository at this point in the history

Commits on Sep 18, 2020

  1. use logsumexp, clamp and softmax

    marioyc committed Sep 18, 2020
    Configuration menu
    Copy the full SHA
    a137895 View commit details
    Browse the repository at this point in the history

  2. change optimizer hyperparameters

    @marioyc
    marioyc committed Sep 18, 2020
    Configuration menu
    Copy the full SHA
    a80c86d View commit details
    Browse the repository at this point in the history

  3. add batch_size argument

    @marioyc
    marioyc committed Sep 18, 2020
    Configuration menu
    Copy the full SHA
    7106df5 View commit details
    Browse the repository at this point in the history

Commits on Oct 8, 2020

  1. simplify training script

    @marioyc
    marioyc committed Oct 8, 2020
    Configuration menu
    Copy the full SHA
    ca4b9b0 View commit details
    Browse the repository at this point in the history

  2. remove debug statistics

    @marioyc
    marioyc committed Oct 8, 2020
    Configuration menu
    Copy the full SHA
    02e8779 View commit details
    Browse the repository at this point in the history