arXiv cs.AI· Rajesh Mangannavar, Pranay Dugar, Prasad Tadepalli·· 15 小时前AI 评分27
GADAR：用动作排序实现经典规划跨域泛化
GADAR: Generalizing Across Domains via Action Ranking for Classical Planning
AI 导读
GADAR 提出一种以域描述为输入的策略 π(s, G, D)，无需搜索即可在训练中未见过的域上构造接地动作，同一网络可运行于所有域。在八个基准域的留一域零样本测试中，单策略解决 58.3% 测试实例，仅比专用单域模型低 1 个百分点；零样本平均解决 22.6%，随机选择为 3.3%，去掉链层的同表示仅 0.6%，在留出的 Visitall 上达 68%。
正文 · 原文
Abstract:Learned policies for classical planning act without search, but each is tied to the domain it was trained on: network modules per action schema, parameters per predicate, or vocabulary-sized encodings mean a trained policy cannot even be executed on a new domain's predicates and action schemas. We present GADAR (Generalizing Across Domains via Action Ranking), a policy that takes the domain description as input, {\pi}(s, G, D), and constructs grounded actions in domains never seen in training, without search. Symbols are described by the roles they play in the domain rather than by their names, in three layers that each extend the previous one: (i) a lifted domain layer embeds D in every state graph through structural signatures; (ii) a binding layer ties each ground action's applicability to the lifted preconditions it instantiates; and (iii) a chain layer states which schema produces what another needs and how far each schema stands from the goal. The same network therefore runs on every domain, seen or unseen. We evaluate zero-shot generalization leave-one-domain-out over eight benchmark domains. A single GADAR policy trained on seven domains solves 58.3% of their test instances, one point below the 59.3% of dedicated single-domain GADAR models, so one policy serves many domains at no cost in coverage; a multi-task control that keeps symbol identity in its weights, while strong on some of the domains it trains on, transfers to none of the held-out ones. Zero-shot, GADAR executes on every held-out domain and exceeds random choice under the same executor on the large test instances of all eight: it solves 22.6% of them on average, against 3.3% for random choice and 0.6% for the same representation without the chain layer, and reaches 68% on held-out Visitall. Zero-shot coverage nonetheless remains well below in-domain coverage on most domains, and we analyze where it is weakest.
| Comments: | 15 pages, 2 figures, 4 out of 15 pages appendix |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.6; I.2.9 |
| Cite as: | arXiv:2610.34868 [cs.AI] |
| (or arXiv:2610.34868v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34868 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rajesh Mangannavar [view email]
[v1]
Mon, 26 Oct 2026 05:30:31 UTC (524 KB)
来源：arXiv cs.AI · arxiv.org