让智能体像编程一样不断积累和优化可复用的技能程序。
Evolving Programmatic Skill Networks
- 用符号程序构建可组合的技能网络，支持持续学习。
- 在MineDojo和Crafter上实现快速适应与强泛化能力。
- 机制类比神经网络训练，适合长期自主学习场景。
我们研究开放式具身环境中持续技能获取问题，即智能体需构建、优化并复用不断增长的可执行技能库。提出程序化技能网络（PSN），将技能表示为可执行的符号程序，并通过经验演化其组合结构。PSN基于大语言模型实现三大核心机制：(1) \\_opreflect，用于技能组合中的结构化故障定位；(2) 基于成熟度感知的更新门控，稳定可靠技能同时保持不确定技能的可塑性；(3) 回滚验证下的标准结构重构，维持网络紧凑性。进一步发现PSN的学习动态与神经网络训练存在结构相似性。在MineDojo和Crafter上的实验表明，该方法具备鲁棒的技能复用能力、快速适应性及对开放任务分布的强大泛化性能。
原文摘要 · Abstract (English)
We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)~\opreflect for structured fault localization over skill compositions, (2)~progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3)~canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.
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。