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

Add requirements for use with ReinforcementLearning.jl #8

Open
hdavid16 opened this issue Apr 20, 2021 · 4 comments
Open

Add requirements for use with ReinforcementLearning.jl #8

hdavid16 opened this issue Apr 20, 2021 · 4 comments
Labels
enhancement New feature or request

Comments

@hdavid16
Copy link
Owner

and any other things required for ReinforcementLearning.jl
@hdavid16 hdavid16 added the enhancement New feature or request label Apr 20, 2021
@hdavid16
Copy link
Owner Author

hdavid16 commented Apr 22, 2021 •
edited
Loading

  • action space
  • state space
  • state

@hdavid16 hdavid16 changed the title Add action space and observation space for RL Add requirements for use with ReinforcementLearning.jl Apr 22, 2021
@hdavid16
Copy link
Owner Author

Need to fix action space now that producers can be intermediate nodes

@hdavid16
Copy link
Owner Author

The minimum requirements for defining an environment have been defined.
However, this requires importing RLBase and extending the functions within RLBase for SupplyChainEnv. ReinforcementLearning.jl seems to be going through some changes since RLBase is now archived. Will follow up on this before moving the spaces, state, and action functions as extensions to RLBase functions.

hdavid16 added a commit that referenced this issue Nov 24, 2022
@hdavid16
-remove reexport
e7c9e09 
-rename topological_sort to to sort_topological to avoid clashing with unused function in Graphs.jl
-define state_space, action_space, and state functions for RL (#8)
@hdavid16 hdavid16 mentioned this issue Nov 24, 2022
Merged
@hdavid16
Copy link
Owner Author

Minimum requirements are met, but have not been defined as RLBase functions. When this is done, IntervalSets will need to be used to generate the Interval{:closed,:open} for each element of the state and action spaces.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@hdavid16