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.

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

Unit wiped reward not considered for sparse reward in wipe environment #418

Open
LabChameleon opened this issue Aug 10, 2023 · 0 comments
Open

Comments

@LabChameleon
Copy link

LabChameleon commented Aug 10, 2023

Hi,

I am confused about the sparse reward signal of the table wipe environment. It says in the environment's reward function that:

def reward(self, action=None):
"""
Reward function for the task.
Sparse un-normalized reward:
- a discrete reward of self.unit_wiped_reward is provided per single dirt (peg) wiped during this step
- a discrete reward of self.task_complete_reward is provided if all dirt is wiped

Hence, I suspect to get a reward for every wiped dirt peg and an additional reward, if all dirt has been wiped with the sparse reward signal.

However, the unit_wiped_reward is only given if reward-shaping (non-sparse reward) is being used:

if self.reward_shaping:
reward += self.unit_wiped_reward

This seems inconsistent to me. Do I misunderstand something here or should the unit_wiped_reward be considered in the sparse reward signal as well?

Thank you for your help!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant