Rapfi用小模型+增量更新，在无GPU下击败顶尖围棋AI
Rapfi: Distilling Efficient Neural Network for the Game of Gomoku
- 用模式码本压缩大模型，构建极简神经网络
- 计算量少于大模型千倍，精度接近ResNet
- 适合资源受限环境，对战游戏开发者必看
游戏在推动人工智能发展方面具有关键作用，基于神经网络的智能体虽表现优异，但往往需要大量计算资源。本文提出Rapfi，一种高效的五子棋智能体，在计算资源受限环境下超越基于CNN的代理。Rapfi采用从大模型中蒸馏出的基于模式的码本构建紧凑神经网络，并引入增量更新机制，在输入变化较小时显著降低计算开销。该网络所需计算量仅为大型网络（如ResNet）的数个数量级，却能达到相近精度。得益于增量更新，深度优先搜索（如Alpha-Beta剪枝）被大幅加速。经精心调优评估与搜索策略，Rapfi在无加速器（如GPU）条件下，实力超越基于AlphaZero算法的最强开源五子棋AI Katagomo。Rapfi在Botzone平台520个五子棋代理中排名第一，并夺得2024年GomoCup冠军。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。