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

Interpretability in realistic environments #14

Open
wants to merge 12 commits into
base: master
Choose a base branch
from
Open

Interpretability in realistic environments #14

wants to merge 12 commits into from

Commits on Feb 3, 2020

  1. Runner script to sparify reward models for PointMaze

    @AdamGleave
    AdamGleave committed Feb 3, 2020
    Configuration menu
    Copy the full SHA
    aab2933 View commit details
    Browse the repository at this point in the history

Commits on Feb 4, 2020

  1. Merge remote-tracking branch 'origin/master' into hidim-interpretability

    @AdamGleave
    AdamGleave committed Feb 4, 2020
    Configuration menu
    Copy the full SHA
    728bb1b View commit details
    Browse the repository at this point in the history

Commits on Feb 5, 2020

  1. Rewards: refactor to have common GymHardcodedReward base class

    @AdamGleave
    AdamGleave committed Feb 5, 2020
    Configuration menu
    Copy the full SHA
    11672dd View commit details
    Browse the repository at this point in the history

  2. Bugfix in PointMassGroundTruth: use next observation like step()

    @AdamGleave
    AdamGleave committed Feb 5, 2020
    Configuration menu
    Copy the full SHA
    fb67e24 View commit details
    Browse the repository at this point in the history

  3. Fixed LunarLander environment and ground-truth reward model

    @AdamGleave
    AdamGleave committed Feb 5, 2020
    Configuration menu
    Copy the full SHA
    28e48ad View commit details
    Browse the repository at this point in the history

Commits on Mar 1, 2020

  1. PointMass figure tweak: include newline in captions

    @AdamGleave
    AdamGleave committed Mar 1, 2020
    Configuration menu
    Copy the full SHA
    ce79488 View commit details
    Browse the repository at this point in the history

  2. LunarLander: properly shaped reward

    @AdamGleave
    AdamGleave committed Mar 1, 2020
    Configuration menu
    Copy the full SHA
    b298cf8 View commit details
    Browse the repository at this point in the history

  3. Figure tweaks

    @AdamGleave
    AdamGleave committed Mar 1, 2020
    Configuration menu
    Copy the full SHA
    6cba962 View commit details
    Browse the repository at this point in the history

  4. Expert demo configs for LunarLander

    @AdamGleave
    AdamGleave committed Mar 1, 2020
    Configuration menu
    Copy the full SHA
    802774c View commit details
    Browse the repository at this point in the history

  5. Prototype helper methods for interpretability

    @AdamGleave
    AdamGleave committed Mar 1, 2020
    Configuration menu
    Copy the full SHA
    cf9ebc2 View commit details
    Browse the repository at this point in the history

  6. Merge remote-tracking branch 'origin/master' into hidim-interpretability

    @AdamGleave
    AdamGleave committed Mar 1, 2020
    Configuration menu
    Copy the full SHA
    49a0c96 View commit details
    Browse the repository at this point in the history

Commits on Mar 2, 2020

  1. Bugfix: time limit in lunar lander

    @AdamGleave
    AdamGleave committed Mar 2, 2020
    Configuration menu
    Copy the full SHA
    ad16879 View commit details
    Browse the repository at this point in the history