Probabilistic usage of subsequent buckets #3556
Closed
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
|
I think this should only be done when |
xoto10
pushed a commit
to xoto10/stockfish-xoto10
that referenced
this pull request
Jun 15, 2021
Yes, like in #3492 |
|
can you please rebase this test on the new net, correct it for the 'adjusted' argument of evaluate, and give it one more test on fishtest? |
|
@vondele Direct LTC? |
|
yes, that's fine with me. |
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Outdated suggestions cannot be applied.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.
After conducting a series of experimental tests, it seems that using a subsequent bucket to have a second opinion on the evaluation of a position can be beneficial. However, the precise condition when to call is challenging to find and maybe there is even no such condition, so we just do it probabilistically. This patch also serves to smooth the transition between buckets since the current implementation is quite drastic in changing buckets at the boundary piece counts.
STC:
LLR: 2.96 (-2.94,2.94) <-0.50,2.50>
Total: 56064 W: 4950 L: 4744 D: 46370
Ptnml(0-2): 185, 3831, 19794, 4037, 185
https://tests.stockfishchess.org/tests/view/60c74bbd457376eb8bcaaf4c
LTC:
LLR: 2.97 (-2.94,2.94) <0.50,3.50>
Total: 60648 W: 2104 L: 1929 D: 56615
Ptnml(0-2): 25, 1739, 26629, 1898, 33
https://tests.stockfishchess.org/tests/view/60c7b780457376eb8bcaafb1
Bench: 4971722