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

Algorithm: Option Critic methods #278

Draft
wants to merge 22 commits into
base: master
Choose a base branch
from
Draft

Algorithm: Option Critic methods #278

wants to merge 22 commits into from

Commits on Sep 23, 2022

  1. [WIP] OC

    @DavidSlayback
    DavidSlayback committed Sep 23, 2022
    Configuration menu
    Copy the full SHA
    3b49f85 View commit details
    Browse the repository at this point in the history

Commits on Sep 24, 2022

  1. [WIP] dqoc

    @DavidSlayback
    DavidSlayback committed Sep 24, 2022
    Configuration menu
    Copy the full SHA
    30e4928 View commit details
    Browse the repository at this point in the history

Commits on Sep 26, 2022

  1. Getting close. Need to figure out the terminal observation thing ion … 

    …envpool
    @DavidSlayback
    DavidSlayback committed Sep 26, 2022
    Configuration menu
    Copy the full SHA
    ca98f83 View commit details
    Browse the repository at this point in the history

  2. Welp, it runs! Still having issues with timelimit truncation

    @DavidSlayback
    DavidSlayback committed Sep 26, 2022
    Configuration menu
    Copy the full SHA
    972aeed View commit details
    Browse the repository at this point in the history

  3. Switch to gym builtins. Just need a replay buffer

    @DavidSlayback
    DavidSlayback committed Sep 26, 2022
    Configuration menu
    Copy the full SHA
    3ca34dd View commit details
    Browse the repository at this point in the history

Commits on Sep 27, 2022

  1. Runs all the way through, needs tests 

    It's slow, but I'd expect that for an algorithm that updates the actors EVERY TIMESTEP

Need to make sure it matches performance
    @DavidSlayback
    DavidSlayback committed Sep 27, 2022
    Configuration menu
    Copy the full SHA
    adff9bc View commit details
    Browse the repository at this point in the history

  2. A2OC WIP

    @DavidSlayback
    DavidSlayback committed Sep 27, 2022
    Configuration menu
    Copy the full SHA
    1904daf View commit details
    Browse the repository at this point in the history

  3. Runs through, need to verify the sign

    @DavidSlayback
    DavidSlayback committed Sep 27, 2022
    Configuration menu
    Copy the full SHA
    d5624df View commit details
    Browse the repository at this point in the history

Commits on Sep 28, 2022

  1. [WIP] Hoc...tons of notes not here

    @DavidSlayback
    DavidSlayback committed Sep 28, 2022
    Configuration menu
    Copy the full SHA
    57073f6 View commit details
    Browse the repository at this point in the history

Commits on Sep 29, 2022

  1. [WIP] PPOC

    @DavidSlayback
    DavidSlayback committed Sep 29, 2022
    Configuration menu
    Copy the full SHA
    5178eea View commit details
    Browse the repository at this point in the history

  2. Thinking

    @DavidSlayback
    DavidSlayback committed Sep 29, 2022
    Configuration menu
    Copy the full SHA
    f9e87d6 View commit details
    Browse the repository at this point in the history

Commits on Sep 30, 2022

  1. Notes on errors

    @DavidSlayback
    DavidSlayback committed Sep 30, 2022
    Configuration menu
    Copy the full SHA
    7fb5f6a View commit details
    Browse the repository at this point in the history

Commits on Oct 2, 2022

  1. Getting there

    @DavidSlayback
    DavidSlayback committed Oct 2, 2022
    Configuration menu
    Copy the full SHA
    6b981d2 View commit details
    Browse the repository at this point in the history

Commits on Oct 3, 2022

  1. My version works, now to lobotomize it into the original form!

    @DavidSlayback
    DavidSlayback committed Oct 3, 2022
    Configuration menu
    Copy the full SHA
    6c8d07e View commit details
    Browse the repository at this point in the history

  2. Factor termination into inter-option policy loss

    @DavidSlayback
    DavidSlayback committed Oct 3, 2022
    Configuration menu
    Copy the full SHA
    99730da View commit details
    Browse the repository at this point in the history

  3. Merge branch 'vwxyzjn:master' into algorithm/oc

    @DavidSlayback
    DavidSlayback committed Oct 3, 2022
    Configuration menu
    Copy the full SHA
    9707f6c View commit details
    Browse the repository at this point in the history

Commits on Oct 4, 2022

  1. Merge branch 'vwxyzjn:master' into algorithm/oc

    @DavidSlayback
    DavidSlayback committed Oct 4, 2022
    Configuration menu
    Copy the full SHA
    9d3526c View commit details
    Browse the repository at this point in the history

Commits on Oct 6, 2022

  1. Merge branch 'vwxyzjn:master' into algorithm/oc

    @DavidSlayback
    DavidSlayback committed Oct 6, 2022
    Configuration menu
    Copy the full SHA
    ec50907 View commit details
    Browse the repository at this point in the history

Commits on Oct 14, 2022

  1. Merge branch 'vwxyzjn:master' into algorithm/oc

    @DavidSlayback
    DavidSlayback committed Oct 14, 2022
    Configuration menu
    Copy the full SHA
    4bdecf9 View commit details
    Browse the repository at this point in the history

Commits on Oct 15, 2022

  1. Recent updates 

    1) LSTM A2OC
2) Multi-update critic
3) Most of IOC
4) Some refactoring of ppoc
    @DavidSlayback
    DavidSlayback committed Oct 15, 2022
    Configuration menu
    Copy the full SHA
    15fdfb3 View commit details
    Browse the repository at this point in the history

Commits on Oct 16, 2022

  1. Additional algorithms

    @DavidSlayback
    DavidSlayback committed Oct 16, 2022
    Configuration menu
    Copy the full SHA
    d175e39 View commit details
    Browse the repository at this point in the history

Commits on Oct 20, 2022

  1. Merge branch 'vwxyzjn:master' into algorithm/oc

    @DavidSlayback
    DavidSlayback committed Oct 20, 2022
    Configuration menu
    Copy the full SHA
    5d5fbcb View commit details
    Browse the repository at this point in the history