Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2503.13178 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910878920605696 |
|---|---|
| author | Jin, Zhanggen Duan, Haobin Hang, Zhiyang |
| author_facet | Jin, Zhanggen Duan, Haobin Hang, Zhiyang |
| contents | Games have played a pivotal role in advancing artificial intelligence, with AI agents using sophisticated techniques to compete. Despite the success of neural network based game AIs, their performance often requires significant computational resources. In this paper, we present Rapfi, an efficient Gomoku agent that outperforms CNN-based agents in limited computation environments. Rapfi leverages a compact neural network with a pattern-based codebook distilled from CNNs, and an incremental update scheme that minimizes computation when input changes are minor. This new network uses computation that is orders of magnitude less to reach a similar accuracy of much larger neural networks such as Resnet. Thanks to our incremental update scheme, depth-first search methods such as the alpha-beta search can be significantly accelerated. With a carefully tuned evaluation and search, Rapfi reached strength surpassing Katagomo, the strongest open-source Gomoku AI based on AlphaZero's algorithm, under limited computational resources where accelerators like GPUs are absent. Rapfi ranked first among 520 Gomoku agents on Botzone and won the championship in GomoCup 2024. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13178 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rapfi: Distilling Efficient Neural Network for the Game of Gomoku Jin, Zhanggen Duan, Haobin Hang, Zhiyang Artificial Intelligence Machine Learning Games have played a pivotal role in advancing artificial intelligence, with AI agents using sophisticated techniques to compete. Despite the success of neural network based game AIs, their performance often requires significant computational resources. In this paper, we present Rapfi, an efficient Gomoku agent that outperforms CNN-based agents in limited computation environments. Rapfi leverages a compact neural network with a pattern-based codebook distilled from CNNs, and an incremental update scheme that minimizes computation when input changes are minor. This new network uses computation that is orders of magnitude less to reach a similar accuracy of much larger neural networks such as Resnet. Thanks to our incremental update scheme, depth-first search methods such as the alpha-beta search can be significantly accelerated. With a carefully tuned evaluation and search, Rapfi reached strength surpassing Katagomo, the strongest open-source Gomoku AI based on AlphaZero's algorithm, under limited computational resources where accelerators like GPUs are absent. Rapfi ranked first among 520 Gomoku agents on Botzone and won the championship in GomoCup 2024. |
| title | Rapfi: Distilling Efficient Neural Network for the Game of Gomoku |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2503.13178 |