Use the best move eval instead of highest eval for temperature cutoff. #772
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
|
Looking back at #568 I suppose it does say "best move" although I would think MCTS' "best" is most visited instead of highest eval. ?? |
Mardak
commented
Jun 6, 2019
mooskagh
approved these changes
Jun 10, 2019
mooskagh
approved these changes
Jun 10, 2019
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Outdated suggestions cannot be applied.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.
r?@mooskagh The current implementation didn't seem like it supports AlphaZero's
by softmax sam- pling with a temperature of 10.0 among moves for which the value was no more than 1% away from the best move for the first 30 pliesIn particular, a random single visit with high eval towards the end of limited node search could prevent selecting moves that got more visits.