Fix bootstrapping on episode timeout #574
Merged
Conversation
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
vincentpierre
approved these changes
Apr 4, 2018
Contributor
vincentpierre
left a comment
vincentpierre
left a comment
There was a problem hiding this comment.
Not happy about changing process_experiences, might break the trainers someone else implemented
mmattar
approved these changes
Apr 6, 2018
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Value estimate bootstrapping upon episode timeout (ie
max_stepsreached) was incorrectly using observation from new episode, rather than final observation from current episode. This PR addresses this, and improves performance for environments in which the "end of the episode" is an arbitrary timeout (such as 3DBall, Reacher, and Crawler).