用自改进生成高质量规划，比传统方法更快更优。
Self-Improvement for Fast, High-Quality Plan Generation
- 用解码器型Transformer结合图搜索，从低质量数据自迭代提升规划质量。
- 在4个领域平均缩短30%计划长度，超80%计划达最优，且推理延迟亚指数增长。
- 适合需要快速生成高质量规划的智能系统，如机器人、自动化决策。
基于合成规划数据训练的生成模型是通用规划的有前景方法。现有工作多关注是否存在可行解，而非高质量解。本文解决高质规划这一计算难题，在亚指数时间内实现。首先，证明在最优数据下，仅解码器结构的Transformer可为未见问题实例生成高质量规划。其次，提出一种自改进机制：利用多个模型调用与图搜索生成优化后的规划，用于模型微调。在四个领域（Blocksworld、Logistics、Labyrinth、Sokoban）的实验表明，相比源符号规划器，平均计划长度减少30%，超过80%的计划达到已知最优；通过推理时搜索进一步提升质量。模型延迟随规模增长呈亚指数级，优于对比的满足性与最优符号规划器。结果表明，生成模型的自改进为高质量规划生成提供了可扩展方案。
原文摘要 · Abstract (English)
Generative models trained on synthetic plan data are a promising approach to generalized planning. Recent work has focused on finding any valid plan, rather than a high-quality solution. We address the challenge of producing high-quality plans, a computationally hard problem, in sub-exponential time. First, we demonstrate that, given optimal data, a decoder-only transformer can generate high-quality plans for unseen problem instances. Second, we show how to self-improve an initial model trained on sub-optimal data. Each round of self-improvement combines multiple model calls with graph search to generate improved plans, used for model fine-tuning. An experimental study on four domains: Blocksworld, Logistics, Labyrinth, and Sokoban, shows on average a 30% reduction in plan length over the source symbolic planner, with over 80% of plans being optimal, where the optimum is known. Plan quality is further improved by inference-time search. The model's latency scales sub-exponentially in contrast to the satisficing and optimal symbolic planners to which we compare. Together, these results suggest that self-improvement with generative models offers a scalable approach for high-quality plan generation.
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。