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

arXiv: https://arxiv.org/abs/2605.18674 · HTML: https://mlsanity.com/paper/2605.18674/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 18 of 18)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [The Logic of Graph Neural Networks](https://mlsanity.com/paper/2104.14624/) (2021)
- [ASNets: Deep Learning for Generalised Planning](https://mlsanity.com/paper/1908.01362/) (2019)
- [Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits](https://mlsanity.com/paper/2109.10129/) (2021)
- [Systematic Generalization with Edge Transformers](https://mlsanity.com/paper/2112.00578/) (2021)
- [Generalized Planning With Deep Reinforcement Learning](https://mlsanity.com/paper/2005.02305/) (2020)
- [Learning Generalized Policies Without Supervision Using GNNs](https://mlsanity.com/paper/2205.06002/) (2022)
- [Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning](https://mlsanity.com/paper/2403.16508/) (2024)
- [Transfer of Deep Reactive Policies for MDP Planning](https://mlsanity.com/paper/1810.11488/) (2018)
- [Towards Principled Graph Transformers](https://mlsanity.com/paper/2401.10119/) (2024)
- [Symmetries and Expressive Requirements for Learning General Policies](https://mlsanity.com/paper/2409.15892/) (2024)
- [General Policies, Subgoal Structure, and Planning Width](https://mlsanity.com/paper/2311.05490/) (2023)
- [Learning More Expressive General Policies for Classical Planning Domains](https://mlsanity.com/paper/2403.11734/) (2024)
- [First-Order Representation Languages for Goal-Conditioned RL](https://mlsanity.com/paper/2512.19355/) (2025)
- [Learning General Policies with Policy Gradient Methods](https://mlsanity.com/paper/2512.19366/) (2025)
- [Sketch Decompositions for Classical Planning via Deep Reinforcement Learning](https://mlsanity.com/paper/2412.08574/) (2024)
- [Learning Efficiency Meets Symmetry Breaking](https://mlsanity.com/paper/2504.19738/) (2025)

## Abstract (arXiv)

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 C2 logic fragment. Our policies achieve new state-of-the-art performance, significantly surpassing prior work, including the classical planner LAMA.