Open
Conversation
rohanpsingh
force-pushed
the
dev/vectorized-training
branch
from
8c87618 to
7f88d88
Compare
rohanpsingh
force-pushed
the
dev/vectorized-training
branch
3 times, most recently
from
cc8003a to
0b06db4
Compare
When num_envs_per_worker > 1, the code correctly computed fewer workers but then created n_proc workers anyway, spawning far more environments than intended.
get_data() returns a BatchData dataclass, not a dict. The dict-style subscript access would crash with TypeError at runtime.
The auto-reset was replacing the terminal obs with the reset obs, causing incorrect value bootstrapping for truncated episodes. Now stores terminal_observation in info dict and uses it for bootstrapping.
The vectorized _sample_vectorized method wasn't tracking completed episode lengths and rewards, resulting in nan metrics during training.
rohanpsingh
force-pushed
the
dev/vectorized-training
branch
from
f117109 to
4c665fa
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.