Research Papers 论文研究 1d ago Updated 20h ago 更新于 20小时前 44

DraftFM: A Foundation Model for Day-Zero Drafting in Magic: The Gathering DraftFM:面向《万智牌》零日选牌的基础模型

DraftFM is a discrete-choice policy that enables "day-zero" drafting predictions for unseen Magic: The Gathering expansions before any draft logs exist Cards are encoded as frozen 775-dimensional vectors from public card records, structured features, and fixed text embeddings—no card identities, set identities, or usage statistics are used A 1.6M-parameter network trained on 149M human picks from 29 expansions achieved 50.8%, 60.4%, and 56.7% top-1 agreement on three entirely withheld expansions DraftFM是首个针对万智牌"零日drafting"(Day-Zero Drafting)场景的基础模型,在无任何实际选牌数据的情况下即可对新扩展包进行卡牌评分 模型采用160万参数架构,将每张卡牌编码为775维固定特征向量(含公开记录、结构化特征和文本嵌入),完全不依赖卡牌身份、套牌标识或使用统计 在1.49亿次人类选牌(29个扩展包)上训练,对3个完全保留扩展包的预测top-1一致性达50.8%-60.4%,远超均匀随机基准(约7%) 模型成功预测未发布套牌"The Hobbit"的卡牌排名,密封结果在发布前36小时公开,与6位独立专家的一致性达到专家间相互一致的水平 该研究证明了在零样

58
Hot 热度
72
Quality 质量
62
Impact 影响力

Analysis 深度分析

TL;DR

  • DraftFM is a discrete-choice policy that enables "day-zero" drafting predictions for unseen Magic: The Gathering expansions before any draft logs exist
  • Cards are encoded as frozen 775-dimensional vectors from public card records, structured features, and fixed text embeddings—no card identities, set identities, or usage statistics are used
  • A 1.6M-parameter network trained on 149M human picks from 29 expansions achieved 50.8%, 60.4%, and 56.7% top-1 agreement on three entirely withheld expansions (vs. ~7% uniform chance)
  • The same architecture refitted on all 32 observed expansions produced a sealed card ranking for the unreleased set The Hobbit, published ~36 hours before it became draftable
  • The sealed ranking agreed with six independent expert reviewers roughly as much as those reviewers agreed with each other

Why It Matters

This work demonstrates a practical application of transfer learning and zero-shot generalization in a complex, high-dimensional discrete-choice domain where training data for new environments does not yet exist. For AI practitioners, it shows how carefully designed feature representations can enable models to generalize to entirely unseen categories without retraining, which has broad implications for recommendation systems, market entry prediction, and any domain where new items appear before behavioral data is available.

Technical Details

  • Architecture: A compact 1.6-million-parameter neural network functioning as a discrete-choice policy that scores exactly the cards in the current pack, conditioned on the drafted pool and draft state
  • Feature Engineering: Every card is represented as a frozen 775-dimensional vector derived from public card records, structured features, and a fixed text embedding—ensuring no leakage of card identities, set identities, or usage statistics into the model
  • Training Data: 149 million human picks aggregated from 29 Magic: The Gathering expansions
  • Evaluation: Three expansions were withheld entirely during training; top-1 agreement rates of 50.8%, 60.4%, and 56.7% were achieved against human picks, compared to ~7% for uniform random selection
  • Real-World Deployment: The model was refitted on all 32 observed expansions to produce a card ranking for The Hobbit set before its release, with cryptographic sealing of the prediction and validation against six independent expert reviewers

Industry Insight

  • The "frozen feature + lightweight head" paradigm demonstrated here is directly transferable to recommendation systems launching new products, where historical interaction data is absent but rich metadata is available
  • The cryptographic sealing and pre-release validation approach sets a strong precedent for trustworthy AI deployment in time-sensitive domains, showing how model predictions can be made tamper-evident and auditable
  • The near-expert-level agreement suggests that well-regularized, metadata-driven models can approximate human expertise in complex strategic domains, opening possibilities for AI-assisted decision support in competitive gaming, forecasting, and resource allocation

TL;DR

  • DraftFM是首个针对万智牌"零日drafting"(Day-Zero Drafting)场景的基础模型,在无任何实际选牌数据的情况下即可对新扩展包进行卡牌评分
  • 模型采用160万参数架构,将每张卡牌编码为775维固定特征向量(含公开记录、结构化特征和文本嵌入),完全不依赖卡牌身份、套牌标识或使用统计
  • 在1.49亿次人类选牌(29个扩展包)上训练,对3个完全保留扩展包的预测top-1一致性达50.8%-60.4%,远超均匀随机基准(约7%)
  • 模型成功预测未发布套牌"The Hobbit"的卡牌排名,密封结果在发布前36小时公开,与6位独立专家的一致性达到专家间相互一致的水平
  • 该研究证明了在零样本场景下,基于结构化特征和文本嵌入的离散选择策略可有效泛化至全新领域

为什么值得看

这篇文章展示了AI在完全未知领域(新扩展包drafting)中实现零样本泛化的能力,为游戏AI、推荐系统和零样本决策问题提供了重要参考。其"Day-Zero"方法论对需要快速适应新环境的AI系统具有启发意义。

技术解析

  • 模型架构:160万参数的离散选择策略网络,输入为775维固定特征向量(公开卡牌记录+结构化特征+固定文本嵌入),无卡牌身份、套牌标识或使用统计依赖
  • 训练数据:1.49亿次人类选牌记录,来自29个已发布扩展包
  • 评估方法:在3个完全保留的扩展包上进行held-out预测,top-1一致性达50.8%、60.4%、56.7%(均匀随机基准约7%)
  • 零样本验证:为未发布套牌"The Hobbit"生成密封卡牌排名,在发布前36小时公开,与6位独立专家的一致性达到专家间相互一致的水平
  • 创新点:首次系统研究"Day-Zero"场景(新扩展包发布时无任何实际选牌数据),证明基于结构化特征的模型可泛化至全新领域

行业启示

  • 零样本泛化能力:证明AI模型可在完全未知领域(无历史数据)实现有效决策,对游戏AI、推荐系统、金融预测等领域具有借鉴意义
  • 可解释性与可信度:通过密封预测和专家验证建立可信度,为AI决策的透明度和可验证性提供了范例
  • 快速适应新环境:Day-Zero方法论适用于需要快速响应新信息、新环境的场景(如新产品发布、新市场进入)

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Research 科学研究 Gaming 游戏 Training 训练 Dataset 数据集