Gripper penalty and blocking environment #65
Merged
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
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Outdated suggestions cannot be applied.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.
After further testing and usage, we found that applying a reward penalty for effective gripper actions (command close when open and vice versa) speeds up the training of tasks that involve learning to grasp. Specifically, it prevents the policy from excessively opening and closing the gripper. The code has been updated to provide a -0.1 reward penalty by default -- a value that we found to work well for most tasks.
Also, we edited the environment so that gripper actions are executed in a blocking fashion. The environment waits until the gripper fully opens or closes before returning the observation. This also reduces the training time by making the transitions more Markovian.