Harpo fix for conceptual agent saving #111
Open
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
…ng agent - Add checks for empty actions list in select_action method for both exploration and exploitation branches - Return None action when no valid actions are available instead of crashing - Handle None action in play_game method with graceful episode termination - Fix typo in comment (ation -> action) 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
The model saving logic was incorrectly placed inside the testing loop, causing the same model to be saved 250 times consecutively at each milestone (e.g., every 20,000 episodes). This resulted in: - File size fluctuations as saves were repeatedly overwriting - Extremely long save times due to multiple concurrent operations - Wasted I/O and disk space Moved the save check outside the testing loop to ensure models are saved only once per milestone episode. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
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Outdated suggestions cannot be applied.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.
Description
The model saving was happening inside the testing loop, so every time it hit a save milestone), it was saving the same model 250 times. this fix put this out of the test loop
l
Store the model every --eval_each episodes.