用强化学习生成更反直觉、更创意的国际象棋谜题
Generating Creative Chess Puzzles
- 基于棋手引擎搜索数据设计奖励机制，提升谜题独特性
- 反直觉谜题生成率提升10倍，达2.5%，超现有数据集
- 人类专家评价其创意与趣味性媲美经典原创谜题
尽管生成式AI在多个领域快速进步，但生成真正具有创造力、美感和反直觉特性的内容仍是挑战。本文针对国际象棋谜题生成问题，首先对生成式AI架构进行基准测试，随后提出一种基于强化学习的框架，其奖励机制结合棋手引擎搜索统计信息，旨在增强谜题的独特性、反直觉性、多样性与真实性。该方法使反直觉谜题生成率从监督学习的0.22%大幅提升至2.5%，超过现有数据集（2.1%）及最佳Lichess训练模型（0.4%）。生成谜题满足新颖性与多样性标准，保留美学主题，经三位世界知名专家评估，被认为比人工编排的书本谜题更具创意、趣味性和反直觉性，甚至接近经典创作水平。最终产出一本由这些AI生成谜题组成的精选手册，获专家认可为高创造力作品。
原文摘要 · Abstract (English)
While Generative AI rapidly advances in various domains, generating truly creative, aesthetic, and counter-intuitive outputs remains a challenge. This paper presents an approach to tackle these difficulties in the domain of chess puzzles. We start by benchmarking Generative AI architectures, and then introduce an RL framework with novel rewards based on chess engine search statistics to overcome some of those shortcomings. The rewards are designed to enhance a puzzle's uniqueness, counter-intuitiveness, diversity, and realism. Our RL approach dramatically increases counter-intuitive puzzle generation by 10x, from 0.22\% (supervised) to 2.5\%, surpassing existing dataset rates (2.1\%) and the best Lichess-trained model (0.4\%). Our puzzles meet novelty and diversity benchmarks, retain aesthetic themes, and are rated by human experts as more creative, enjoyable, and counter-intuitive than composed book puzzles, even approaching classic compositions. Our final outcome is a curated booklet of these AI-generated puzzles, which is acknowledged for creativity by three world-renowned experts.
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。