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

cartpole ppo train , reward drop #42

Open
SeungyounShin opened this issue Feb 20, 2021 · 1 comment
Open

cartpole ppo train , reward drop #42

SeungyounShin opened this issue Feb 20, 2021 · 1 comment

Comments

@SeungyounShin
Copy link

SeungyounShin commented Feb 20, 2021 •
edited
Loading

if you train ppo far enough likes 3000 episodes or more, rewards got dropped. (like 500 to 30)
@seolhokim seolhokim mentioned this issue Feb 27, 2021
Open
@seolhokim
Copy link

seolhokim commented Feb 27, 2021 •
edited
Loading

@SeungyounShin
PPO is an on-policy algorithm. When you update agent using highly correlated trajectories can makes agent worse. I fixed that #45 for you.

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
@SeungyounShin @seolhokim