Skip to content

Improve Gym wrapper compatibility and add Dopamine documentation #1541

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.

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

Merged
merged 25 commits into from
Jan 8, 2019

Conversation

ervteng
Copy link
Contributor

@ervteng ervteng commented Dec 30, 2018

Changes to Gym Wrapper

  • Added option to use uint8's (0-255) instead of floats (0-1) for visual observations to mimic Atari
  • Added option to flatten branched discrete actions into a single branch
  • Added game_over flag to mimic Atari

Changes to Documentation

  • Added steps on how to integrate with Dopamine library
  • Added example results from GridWorld and VisualBanana using Dopamine

@ervteng ervteng requested review from mmattar and awjuliani December 30, 2018 07:54
Ervin Teng added 2 commits January 4, 2019 18:01
@ervteng ervteng requested a review from mmattar January 5, 2019 02:16
@ervteng ervteng requested a review from mmattar January 7, 2019 23:55
Copy link

@mmattar mmattar left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Last minor comment: the figure boundary is only visible for half of the figure. Applies to both figures.

@ervteng ervteng merged commit 3b572a2 into develop Jan 8, 2019
mantasp added a commit that referenced this pull request Jan 28, 2019
…agents into develop-barracuda

* 'develop-barracuda' of github.com:Unity-Technologies/ml-agents:
  deleted dead meta file and added a note on the OpenGLCore Graphics API
  Barracuda : Updating the documentation (#1607)
  Remove env creation logic from TrainerController (#1562)
  Fix In editor Docker training (#1582)
  Only using multiprocess when --num-runs>1 (#1583)
  Replace AddVectorObs(float[]) and AddVectorObs(List<float>) with a more generic AddVectorObs(IEnumerable<float>) (#1540)
  fixed the windows ctrl-c bug (#1558)
  Improve Gym wrapper compatibility and add Dopamine documentation (#1541)
  Fix typo in documentation (#1516)
  Update curricula brain names for 0.6
  Addressing #1537
  Fix for divide-by-zero error with Discrete Actions  (#1520)
  Documentation tweaks and updates (#1479)
mantasp added a commit that referenced this pull request Jan 29, 2019
* develop-barracuda:
  Backup and restore fixedDeltaTime and maximumDeltaTime on Academy init / shutdown
  Restore global gravity value when Academy gets destroyed
  deleted dead meta file and added a note on the OpenGLCore Graphics API
  Barracuda : Updating the documentation (#1607)
  Remove env creation logic from TrainerController (#1562)
  Fix In editor Docker training (#1582)
  Only using multiprocess when --num-runs>1 (#1583)
  Replace AddVectorObs(float[]) and AddVectorObs(List<float>) with a more generic AddVectorObs(IEnumerable<float>) (#1540)
  fixed the windows ctrl-c bug (#1558)
  Improve Gym wrapper compatibility and add Dopamine documentation (#1541)
  Fix typo in documentation (#1516)
  Update curricula brain names for 0.6
  Addressing #1537
  Fix for divide-by-zero error with Discrete Actions  (#1520)
  Documentation tweaks and updates (#1479)
harperj pushed a commit that referenced this pull request Feb 20, 2019
* Add option to set gym visual observation to uint8

* Add option to flatten branched discrete actions

* Add game_over variable to gym wrapper

* Add guide on how to use Dopamine with the gym wrapper and comparisons with Baselines and PPO
@ervteng ervteng deleted the develop-dopaminegym branch July 9, 2019 21:55
LeSphax pushed a commit to LeSphax/ml-agents-1 that referenced this pull request May 3, 2020
…ty-Technologies#1541)

* Add option to set gym visual observation to uint8

* Add option to flatten branched discrete actions

* Add game_over variable to gym wrapper

* Add guide on how to use Dopamine with the gym wrapper and comparisons with Baselines and PPO
@github-actions github-actions bot locked as resolved and limited conversation to collaborators May 18, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants