Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

• URL: http://arxiv.org/abs/2605.18674v1
• Date: Mon, 18 May 2026 17:15:23 GMT
• Title: Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning
• Abstract summary: Generalized planning aims to learn policies that generalize across collections of instances within a classical planning domain.<n>Recent Graph Neural Network (GNN) approaches have learned nearly perfect policies for several domains.<n>This work improves on the recently published idea of Iterated Width (IW) policies.
• Score: 7.31472912229643
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalized planning aims to learn policies that generalize across collections of instances within a classical planning domain. Recent Graph Neural Network (GNN) approaches have learned nearly perfect policies for several domains. This work improves on the recently published idea of Iterated Width (IW) policies. Therein, the policy broadens its successor scope through an IW-lookahead search that can "jump" over multiple transitions, simplifying the problem structure. Yet, each transition is evaluated individually, leading to unscalable compute costs and expressivity limitations. Furthermore, although IW(1) is attractive because it scales linearly with the number of atoms, it becomes inefficient once thousands of objects are considered, as in the International Planning Competition (IPC) 2023 benchmark. We address both limitations. First, we introduce a vastly more efficient holistic encoding of the entire search tree. It jointly represents IW(1)-reachable states only by their relational differences to the current state, enabling Relational GNNs (R-GNNs) to score all transitions in a single forward pass. Second, we define Abstracted IW(1) to improve scaling through relational abstraction during novelty checks. Rather than testing fully instantiated atoms, it abstracts each atom by replacing all but one argument with its type. The original atom is novel if any of its abstracted forms is novel. This structural compression shifts novelty search scaling from atoms to objects, while preserving meaningful subgoal structure. We evaluate our contributions on the hyperscaling IPC 2023 benchmark and across diverse domains, including domains requiring features beyond the $C_2$ logic fragment. Our policies achieve new state-of-the-art performance, significantly surpassing prior work, including the classical planner LAMA.

Related papers

• Analysis of Optimality of Large Language Models on Planning Problems [12.31072556856411]
  We show that Reasoning-enhanced Large Language Model (LLM) planners track theoretical optimality limits with near-perfect precision.<n>We also study a formally equivalent task, the generalized Path-Star ($P*$) graph, in order to isolate true topological reasoning from semantic priors.
  arXiv  Detail & Related papers  (2026-04-03T09:27:16Z)
• HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature [6.001574550157585]
  We propose a two-stage framework for scalable, zero-shot scientific knowledge graph constructions.<n>We release SPHERE, a benchmark for hierarchical relation extraction.<n>In zero-shot settings, gains reach 10.76% for NER and 26.2% for RE.
  arXiv  Detail & Related papers  (2026-03-24T12:35:10Z)
• One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection [65.11602552904456]
  Universal visual anomaly detection (AD) aims to identify anomaly images and segment anomaly regions towards open and dynamic scenarios.<n>Current methods often struggle with complex prompt engineering, elaborate adaptation modules, and challenging training strategies.<n>This paper presents an embarrassingly simple, general, and effective framework for Universal vision Anomaly Detection (UniADet)
  arXiv  Detail & Related papers  (2026-01-09T06:05:18Z)
• Bearing Syntactic Fruit with Stack-Augmented Neural Networks [59.49467149799849]
  We show that stack-augmented neural networks are more accurate models of human language acquisition than standard architectures.<n>We also propose a modification to the stack RNN architecture that improves hierarchical generalization.
  arXiv  Detail & Related papers  (2025-11-05T15:30:58Z)
• RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Semantic Retrieval based Multi-Trajectory Mamba [86.47790050206306]
  RefAVA++ comprises >2.9 million frames and >75.1k annotated persons in total.<n> RefAtomNet++ advances cross-modal token aggregation through a multi-hierarchical semantic-aligned cross-attention mechanism.<n>Experiments show that RefAtomNet++ establishes new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-10-18T10:41:19Z)
• Learning to Ground Existentially Quantified Goals [10.343546104340962]
  Goal instructions for autonomous AI agents cannot assume that objects have unique names. This raises problems in both classical planning and generalized planning. In this work, we address the goal grounding problem with a novel supervised learning approach.
  arXiv  Detail & Related papers  (2024-09-30T12:49:27Z)
• Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters [59.82088750033897]
  We set up a Generalized FSCL (GFSCL) protocol involving both class- and domain-incremental situations. We find that common continual learning methods have poor generalization ability on unseen domains. In this way, we propose a rehearsal-free framework based on Vision Transformer (ViT) named Contrastive Mixture of Adapters (CMoA)
  arXiv  Detail & Related papers  (2023-02-12T15:18:14Z)
• Vision Transformers: From Semantic Segmentation to Dense Prediction [139.15562023284187]
  We explore the global context learning potentials of vision transformers (ViTs) for dense visual prediction. Our motivation is that through learning global context at full receptive field layer by layer, ViTs may capture stronger long-range dependency information. We formulate a family of Hierarchical Local-Global (HLG) Transformers, characterized by local attention within windows and global-attention across windows in a pyramidal architecture.
  arXiv  Detail & Related papers  (2022-07-19T15:49:35Z)
• Learning Generalized Policies Without Supervision Using GNNs [20.322992960599255]
  We consider the problem of learning generalized policies for classical planning domains using graph neural networks. We use a simple and general GNN architecture and aim at obtaining crisp experimental results. We exploit the relation established between the expressive power of GNNs and the $C_2$ fragment of first-order logic.
  arXiv  Detail & Related papers  (2022-05-12T10:28:46Z)
• Planning and Learning with Adaptive Lookahead [74.39132848733847]
  Policy Iteration (PI) algorithm alternates between greedy one-step policy improvement and policy evaluation. Recent literature shows that multi-step lookahead policy improvement leads to a better convergence rate at the expense of increased complexity per iteration. We propose for the first time to dynamically adapt the multi-step lookahead horizon as a function of the state and of the value estimate.
  arXiv  Detail & Related papers  (2022-01-28T20:26:55Z)
• Hierarchical Prototype Networks for Continual Graph Representation Learning [90.78466005753505]
  We present Hierarchical Prototype Networks (HPNs) which extract different levels of abstract knowledge in the form of prototypes to represent the continuously expanded graphs. We show that HPNs not only outperform state-of-the-art baseline techniques but also consume relatively less memory.
  arXiv  Detail & Related papers  (2021-11-30T14:15:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.