[Versioning] Gymnasium 1.0 incompatibility errors #2484
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2484
Note: Links to docs will display an error until the docs builds have been completed. ❌ 13 New Failures, 5 Unrelated FailuresAs of commit a126b0c with merge base efa5745 ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
matteobettini
approved these changes
Oct 10, 2024
| changes in the Gym API. | ||
| Using gymnasium 1.0 with TorchRL would require significant modifications to your code and may result in: | ||
| * Inaccurate step counting, as the auto-reset feature can cause unpredictable numbers of steps to be executed. | ||
| * Potential data corruption, as the environment may require/produce garbage data during reset steps. |
There was a problem hiding this comment.
Suggested change
| * Potential data corruption, as the environment may require/produce garbage data during reset steps. | |
| * Potential data corruption, as the environment may require/produce invalid data during reset steps. |
| GYMNASIUM_1_ERROR = """RuntimeError: TorchRL does not support gymnasium 1.0 or later versions due to incompatible | ||
| changes in the Gym API. | ||
| Using gymnasium 1.0 with TorchRL would require significant modifications to your code and may result in: | ||
| * Inaccurate step counting, as the auto-reset feature can cause unpredictable numbers of steps to be executed. |
There was a problem hiding this comment.
Suggested change
| * Inaccurate step counting, as the auto-reset feature can cause unpredictable numbers of steps to be executed. | |
| * Inaccurate step counting, the number of step calls to obtain the same amount of data using the autoreset feature will depend on the done frequency of the enviornment. |
| Using gymnasium 1.0 with TorchRL would require significant modifications to your code and may result in: | ||
| * Inaccurate step counting, as the auto-reset feature can cause unpredictable numbers of steps to be executed. | ||
| * Potential data corruption, as the environment may require/produce garbage data during reset steps. | ||
| * Trajectory overlap during data collection. |
There was a problem hiding this comment.
Maybe explain this one too
| * Inaccurate step counting, as the auto-reset feature can cause unpredictable numbers of steps to be executed. | ||
| * Potential data corruption, as the environment may require/produce garbage data during reset steps. | ||
| * Trajectory overlap during data collection. | ||
| * Increased computational overhead, as the library would need to handle the additional complexity of auto-resets. |
There was a problem hiding this comment.
Suggested change
| * Increased computational overhead, as the library would need to handle the additional complexity of auto-resets. | |
| * Increased computational overhead, as auto-resets introduce additional computational complexity. |
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.
Stack from ghstack (oldest at bottom):