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

why every algo reimplements policies that show up in others as well #460

Closed
kirk86 opened this issue Jul 8, 2018 · 2 comments
Closed

why every algo reimplements policies that show up in others as well #460

kirk86 opened this issue Jul 8, 2018 · 2 comments
Labels
question

Comments

@kirk86
Copy link

kirk86 commented Jul 8, 2018

Hi and thank you for this work!. I have noob question. I was wondering why in every algorithm folder there are policies re-implemented. Isn't that a redundancy. Wouldn't it be better to have just one folder with all the policies implemented once and then accordingly use them in every algo, trpo, a2c,..,etc.?
@araffin
Copy link
Contributor

araffin commented Jul 10, 2018

Similar to #445 #413 #400

@araffin araffin mentioned this issue Jul 28, 2018
Closed
@pzhokhov
Copy link
Collaborator

@kirk86 you are absolutely right - it is a redundancy, and it is not great. We have recently merged a large refactor that eliminates most of the code duplication in policies and network building.

AdamGleave pushed a commit to HumanCompatibleAI/baselines that referenced this issue Sep 7, 2019
@DonsetPG @araffin
Add FluidMechanics project (openai#460)
1d55747 
* Adding FluidMechanics project using StableBaseline

* Update projects.rst

* Update Changelog Fenics-DRL
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@araffin @kirk86 @pzhokhov