Added array-like min and max actions#29
Open
beelerchris wants to merge 1 commit into
Open
Conversation
| a = F.relu(self.l1(state)) | ||
| a = F.relu(self.l2(a)) | ||
| return self.max_action * torch.tanh(self.l3(a)) | ||
| return (self.max_action - self.min_action) * ((torch.tanh(self.l3(a)) + 1) / 2) + self.min_action |
There was a problem hiding this comment.
Hi, may I ask the reason why you change here? I have ever tested your code, and comparing with the original one, the performace becomes worse, and the output action results seem very weird.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
torch.clampdoesn't support tensor min and max inputs thereforetorch.minandtorch.maxhave to be used instead.The changes have been tested on Pendulum-v0 and some custom environments with array-like action spaces to ensure clipping and minimum action are handled properly.