经典规划中提升动作模式的可微学习方法研究（arXiv:2605.13282）
Differentiable Learning of Lifted Action Schemas for Classical Planning
AI 导读
一项研究提出新的神经网络架构，在状态完全可观测但动作参数未观测的轨迹数据上，可微地学习经典规划中的提升动作模式。该方法需同时识别观测状态变化中的动作参数并学习动作模式，恢复各规划领域的真值结构，所得到的可微组件可集成到更大的神经符号模型中。实验还包括对观测噪声的鲁棒性、组件消融以及基于槽的动力学模型变体测试。
正文 · 原文
Abstract:Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and relations, and lifted action schemas add or delete these atoms. This compact representation yields strong search heuristics and provides an ideal setting for structural generalization, since lifted relations and action schemas give rise to infinitely many domain instances. A central challenge is to learn these relations and action schemas from data, and recent approaches have addressed this problem using different types of observations. In this work, we develop a novel neural network architecture for learning action schemas from traces where states are fully observed but action arguments are unobserved. The problem is a simplification but an important step towards learning planning domains from sequences of images and action labels, and we aim to solve this simplification in a nearly perfect manner. The challenge lies in learning the action schemas while simultaneously identifying the action arguments from observed state changes. Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure. Additionally, we report experiments on robustness to observation noise, on component ablations, and on a variation related to slot-based dynamics models.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.13282 [cs.AI] |
| (or arXiv:2605.13282v4 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13282 arXiv-issued DOI via DataCite |
Submission history
From: Jonas Reiter [view email]
[v1]
Wed, 13 May 2026 09:59:49 UTC (374 KB)
[v2]
Sun, 24 May 2026 13:53:18 UTC (374 KB)
[v3]
Mon, 9 Nov 2026 13:07:01 UTC (97 KB)
[v4]
Tue, 10 Nov 2026 08:57:59 UTC (89 KB)
来源：arXiv cs.AI · arxiv.org