[RLlib] Fix Single/MultiAgentEnvRunner missing env-to-module connector call in _sample_episodes().
#45517
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
Signed-off-by: sven1977 <[email protected]>
sven1977
requested review from
ArturNiederfahrenhorst and
simonsays1980
as code owners
simonsays1980
approved these changes
May 23, 2024
rllib/algorithms/callbacks.py
Outdated
| 3) Callback `on_episode_step` is fired. | ||
| 4) Another env-to-module connector call is made (even though we won't need any | ||
| RLModule forward pass anymore). We make this additional call to ensure that in | ||
| case users use the connector pipeline to process observations (and write them |
There was a problem hiding this comment.
Ah, very important. Good catch!
| shared_data=self._shared_data, | ||
| ) | ||
| if self.module is not None: | ||
| self._env_to_module( |
There was a problem hiding this comment.
Episode is written in-place, correct?
There was a problem hiding this comment.
Yes, correct.
Some connectors act as preprocessors: read from episode, change the obs, write it right back in.
We should probably make this the default pattern for all connectors that preprocess observations. Right now we have some that do this, but others do NOT write back into the episode and therefore rely on two more connectors around them: AddObsFromEpisodeToBatch AND WriteObsToEpisode. This is causing a lot of confusion right now.
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
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Outdated suggestions cannot be applied.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.
Fix Single/MultiAgentEnvRunner missing env-to-module connector call in
_sample_episodes().The env-to-module connector call on the terminal obs is missing in both Single- and MultiAgentEnvRunners
_sample_episodes()methods. It is, however, properly implemented in both their_sample_timesteps()methods.Why are these changes needed?
Related issue number
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.