Skip to content
This repository was archived by the owner on May 6, 2021. It is now read-only.

Fixes to Pendulum.jl and some standardizing of classical control envs #65

Merged
merged 6 commits into from
Jun 4, 2020
Merged

Fixes to Pendulum.jl and some standardizing of classical control envs #65

merged 6 commits into from
Jun 4, 2020

Conversation

AlexLewandowski
Copy link
Contributor

Changes to classical control envs:

  • asserts that action is in the appropriate action_space

Changes to pendulum:

  • angle_normalize now properly normalizes negative thetas.
  • reset! sets the state values as in OpenAI gym
  • Added an option for discrete actions
  • Sets previously used action

Changes to mountain_car:

  • rename _interact! to _step! for consistency
  • Sets previously used action

Changes to cartpole:

  • rename tau to dt for consistency

findmyway
findmyway reviewed Jun 3, 2020
View reviewed changes
@findmyway findmyway merged commit 5dcada4 into JuliaReinforcementLearning:master Jun 4, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers

@findmyway findmyway findmyway left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@AlexLewandowski @findmyway