Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[WIP] Implement vanila mcts #24

Merged
merged 4 commits into from
Oct 24, 2024
Merged

[WIP] Implement vanila mcts #24

merged 4 commits into from
Oct 24, 2024
+186 −68

Conversation

ziyuwan
Copy link
Collaborator

@ziyuwan ziyuwan commented Oct 22, 2024

Implementation of vanila MCTS, currently only support two kinds of rollout strategy, greedy_by_prm and random_by_lm_prior_prob

@ziyuwan ziyuwan requested a review from KounianhuaDu October 22, 2024 02:18
@ziyuwan ziyuwan self-assigned this Oct 22, 2024
@ziyuwan ziyuwan added the enhancement New feature or request label Oct 22, 2024
@ziyuwan ziyuwan requested a review from YanSong97 October 22, 2024 06:11
@wphtrying
Copy link

wphtrying commented Oct 22, 2024 •
edited by ziyuwan
Loading

When this MR is going to close, would like to try the new MCTS

@ziyuwan
Copy link
Collaborator Author

ziyuwan commented Oct 23, 2024

When this MR is going to close, would like to try the new MCTS

Hi!
You can use bb9b884e0be38e0a99e56e5ee46816d7c0a5365d currently. We still need some efforts to confirm the hyperparameters of MCTS and improve the code structure.

@mengfn mengfn force-pushed the main branch 2 times, most recently from ee4b45c to 10a28ce Compare October 24, 2024 10:46
@KounianhuaDu KounianhuaDu merged commit 1b2aa7b into main Oct 24, 2024
YanSong97 added a commit that referenced this pull request Oct 27, 2024
@YanSong97
OpenR now supports MCTS reasoning! (PR #24)
1c39869
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@KounianhuaDu KounianhuaDu Awaiting requested review from KounianhuaDu

@YanSong97 YanSong97 Awaiting requested review from YanSong97

Assignees

@ziyuwan ziyuwan

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@ziyuwan @wphtrying @KounianhuaDu