Convert quoridor movement action IDs to relative #1232
Merged
+717
−688
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
The original implementation of Quoridor used absolute position numbering for pawn moves, so moving to b3 was always the same action ID, regardless of where the pawn was. This commit changes to using relative action IDs, so moving directly north is always the same action ID, regardless of what square that is moving to.
|
Wow there's really something going on with the wheels test. I've restarted the failed jobs, hopefully this does it. |
|
Looks like they've all passed the point where they usually fail, so 🤞 |
lanctot
added
imported
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Outdated suggestions cannot be applied.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.
The original implementation of Quoridor used absolute position numbering for pawn moves, so moving to b3 was always the same action ID, regardless of where the pawn was. This commit changes to using relative action IDs, so moving directly north is always the same action ID, regardless of what square that is moving to.
See PR #1229 for a deeper discussion of what this change does and why it's only a partial solution to optimzing the game for reinforcement learning.
Fixes #1158