Implement a multi-objective pistonball environment #10
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
wilrop
requested review from
ffelten and
umutucak
and removed request for
ffelten
ffelten
reviewed
Nov 8, 2023
| ) | ||
| self.reward_dim = 3 # [global, local, time] | ||
| self.reward_spaces = { | ||
| f"piston_{i}": Box(low=-np.inf, high=np.inf, shape=(self.reward_dim,), dtype=np.float32) |
There was a problem hiding this comment.
Isn't it possible to have better bounds on this?
|
I've added more informative reward bounds with documentation for how I obtained these bounds. If someone could briefly check whether this makes sense that would be good. I also ran random policies with 50 different seeds to verify whether the rewards were indeed within the specified bounds and everything seemed okay. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I implemented a multi-objective version of Pistonball. This essentially boils down to separating the three components of the original reward function and exposing these as a vector reward instead.