Achieving master level play in 9×9 computer go
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The UCT algorithm uses Monte-Carlo simulation to estimate the value of states in a search tree from the current state. However, the first time a state is encountered, UCT has no knowledge, and is unable to generalise from previous experience. We describe two extensions that address these weaknesses. Our first algorithm, heuristic UCT, incorporates prior knowledge in the form of a value function. The value function can be learned offline, using a linear combination of a million binary features, with weights trained by temporal-difference learning. Our second algorithm, UCT-RAVE, forms a rapid online generalisation based on the value of moves. We applied our algorithms to the domain of 9 • 9 Computer Go, using the program MoGo. Using both heuristic UCT and RAVE, MoGo became the first program to achieve human master level in competitive play. Copyright © 2008.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.004 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it