Cached Environment Wrapper #33
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
…h/minihack into samvelyan/cached_wrapper
facebook-github-bot
added
the
CLA Signed
heiner
approved these changes
Nov 19, 2021
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Outdated suggestions cannot be applied.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.
CachedEnvWrapperby @heiner that uses two queues to emulate a single environment. By making use of several threads, this allows to swap the underlying environment during resetting. Consequently, the tasks wherereset()could be a bottleneck can be made substantially faster.Also added a script that compares the SPS of environments with or without the wrapper. On
MiniHack-MultiRoom-N2-Lava-v0which features comparatively longreset()* ,CachedEnvWrapperspeeds up the SPS approximately two times on a random policy.*This is due to the fact that it triggers a
reset()on MiniGrid's side, recompiles the des-file, and generally has short episodes given all the lava tiles on the grid that instantly kill the agent.