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

Retrain the robot with a reward that penalizes quick action changes. #48

Closed
ll7 opened this issue Aug 27, 2024 · 1 comment · Fixed by #54
Closed

Retrain the robot with a reward that penalizes quick action changes. #48

ll7 opened this issue Aug 27, 2024 · 1 comment · Fixed by #54
Assignees
@ll7
Labels
enhancement New feature or request p2 2nd most important task category RL Reinforcement Learning Issue

Comments

@ll7
Copy link
Owner

ll7 commented Aug 27, 2024

Currently, the robot creates many small actions. This is unrealistic and energy consuming. A new reward should be designed to punish many changes in the picked action.
@ll7 ll7 added enhancement New feature or request p2 2nd most important task category RL Reinforcement Learning Issue labels Aug 27, 2024
@ll7 ll7 self-assigned this Aug 28, 2024
@ll7 ll7 mentioned this issue Sep 17, 2024
Open
@ll7
Copy link
Owner Author

ll7 commented Sep 17, 2024

A new model is trained, but the performance is not optimal:
I don't know why the collision rates aren't better.
image

@ll7 ll7 linked a pull request Sep 17, 2024 that will close this issue
Ll7/issue48 retrain the robot with a reward that penalizes quick action changes #54
Merged
@ll7 ll7 closed this as completed in #54 Sep 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@ll7 ll7

Labels
enhancement New feature or request p2 2nd most important task category RL Reinforcement Learning Issue
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Ll7/issue48 retrain the robot with a reward that penalizes quick action changes ll7/robot_sf_ll7
1 participant
@ll7