用时间与历史信息预测人类走法，模型更小但准确率更高。
Otter: A Time-Aware, History-Conditioned Human Chess AI
- 结合最近20步棋和剩余时间，建模人类下棋的动态过程。
- 在1900-1999分段达到57.38%最高准确率，整体顶1准确率达55.23%。
- 适合研究人类决策行为或轻量级棋类模型的开发者使用。
Otter 是一个参数量为15.3M的人类国际象棋行为预测模型，通过将下棋视为具有时间感知的序列过程，而非孤立分析每个局面。它融合两种条件信号：(1) 移动历史编码器，基于最近20步棋捕捉开局偏好、局势演变及对局中行为趋势；(2) 时间控制模块，根据剩余时间调节预测结果。该模型在1.17亿局Lichess快棋对局的61亿个局面上训练，仅用单块T4 GPU连续训练30天。在移动预测任务中，其顶1准确率为55.23%，顶5准确率达90.95%，优于此前最优模型Maia 2，且参数更少、训练数据更少。在11个等级分区间（<1100至≥2000）中，1900-1999分段表现最佳，准确率达到57.38%。结果表明，将下棋视为时间感知的序列活动，能更精准地模拟人类走法，且可用更小模型实现。代码、训练模型和完整日志已公开。
原文摘要 · Abstract (English)
Otter is a 15.3M-parameter human chess AI that predicts human move selection by modeling play as a time-aware, sequential process rather than treating each position in isolation. It combines two conditioning signals: (1) a move history encoder that conditions predictions on the last 20 moves, capturing opening preferences, positional drift, and intra-game behavioral tendencies; and (2) a time control module that modulates predictions based on clock pressure. Otter is trained on 6.1 billion positions from 117 million Lichess rapid games over 30 days on a single T4 GPU. Otter achieves 55.23% top-1 and 90.95% top-5 move-prediction accuracy, surpassing the prior state-of-the-art human chess model, Maia 2, with far fewer parameters and less training data. Across 11 Elo brackets (<1100 to >=2000), accuracy peaks at 57.38% in the 1900-1999 bracket. These results show that modeling chess as a time-aware, sequential activity yields more human-accurate move prediction than position-only approaches, using a smaller model. Code, trained models, and complete training logs are publicly released.
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。