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

use beta distribution instead of gaussian when you add continuous actions #2

Closed
ethancaballero opened this issue Sep 18, 2017 · 1 comment
Closed

use beta distribution instead of gaussian when you add continuous actions #2

ethancaballero opened this issue Sep 18, 2017 · 1 comment

Comments

@ethancaballero
Copy link

Beta distribution seems to always work better than Gaussian on high dimensional continuous control tasks:

"Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution"
http://proceedings.mlr.press/v70/chou17a/chou17a.pdf
@ikostrikov
Copy link
Owner

Thanks! I will try to implement it sometime later.

@jakefoster954 jakefoster954 mentioned this issue Feb 3, 2021
Open
avivt pushed a commit to avivt/pytorch-a2c-ppo-acktr-gail that referenced this issue Jun 8, 2021
@EvZissel
Merge pull request ikostrikov#2 from avivt/master
f2b656e 
sync with avivt
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ikostrikov @ethancaballero