Research on Improving the AlphaZero Algorithm for Dots and Boxes Strategy Based on the Transformer Framework
Bibliographic record
Abstract
Go, as a board game with simple rules but a complex strategic space, has become an important testing ground for research in reinforcement learning and game intelligence. Addressing the shortcomings of the original AlphaZero algorithm in modeling long-range dependencies and strategy accuracy, this paper proposes an AlphaZero game strategy optimization method based on an improved Transformer architecture. This method replaces the convolutional neural network in AlphaZero with a Transformer encoder structure featuring multi-head attention mechanisms, enabling deep modeling of global board information and precise control over strategic decision-making. By constructing a comprehensive Go game platform that integrates self-play training, Monte Carlo tree search, and a unified strategy-value output mechanism, this paper conducts comparative experiments between the improved algorithm and traditional AlphaZero across multiple metrics. The results show that the improved model performs better in terms of average win rate, training convergence speed, and strategy stability, particularly demonstrating stronger game intelligence and generalization capabilities in complex mid-to-late game situations. This study provides new insights into the optimization of artificial intelligence system architectures for complex board games and lays a structural foundation for the development of intelligent game algorithms.
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.
How this classification was reachedexpand
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 | 0.006 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.002 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".