Author name cluster

Dillon Z. Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

AAAI Conference 2026 Conference Paper

Satisficing and Optimal Generalised Planning via Goal Regression

Dillon Z. Chen
Till Hofmann
Toryn Q. Klassen
Sheila A. McIlraith

Generalised planning (GP) refers to the task of synthesising programs that solve families of related planning problems. We introduce a novel, yet simple method for GP: given a set of training problems, for each problem, compute an optimal plan for each goal atom in some order, perform goal regression on the resulting plans, and lift the corresponding outputs to obtain a set of first-order Condition → Actions rules. The rules collectively constitute a generalised plan that can be executed as is or alternatively be used to prune the planning search space. We formalise and prove the conditions under which our method is guaranteed to learn valid generalised plans and state space pruning axioms for search. Experiments demonstrate significant improvements over state-of-the-art (generalised) planners with respect to the 3 metrics of synthesis cost, planning coverage, and solution quality on various classical and numeric planning domains.

PDF Details DOI

ECAI Conference 2025 Conference Paper

An Operator-Centric Trustable Decision-Making Tool for Planning Ground Logistic Operations of Beluga Aircraft

Rebecca Eifler
Nika Beriachvili
Arthur Bit-Monnot
Dillon Z. Chen
Jan Eisenhut
Jörg Hoffmann 0001
Sylvie Thiébaux
Florent Teichteil-Königsbuch

This paper presents the demonstrator developed in the TUPLES European Union research project for assisting human operators at Airbus to plan Beluga cargo ground logistic operations. The demonstrator features techniques providing robust, explainable, and safe decisions, which all contribute to making our decision-support system trusted by the operators. We have also worked on various planning methods to scale up to the size of the real industrial problem, including hybrid machine learning and symbolic algorithms. We demonstrate the software that was tested by Airbus operators during a user study in Finkenwerder’s production site in May 2025.

Details

ECAI Conference 2025 Conference Paper

Effective Data Generation and Feature Selection in Learning for Planning

Mingyu Hao
Dillon Z. Chen
Felipe W. Trevizan
Sylvie Thiébaux

Previous studies have shown that leveraging data beyond optimal training plans improves the learning of search guidance for planning. Specifically, state ranking information can be extracted from states on optimal plan traces and their siblings. In this paper, we generalise this approach by extracting additional rankings from the A⋆ search tree for generating optimal training plans. As in the previous approach, we incur no additional search effort and negligible computational overhead for data extraction. However, extracting more data in this way may introduce many redundant features and states which slows down training. We formalise the problem of sound, redundant feature pruning and show that it is NP-complete to solve. Furthermore, we introduce several algorithms and approximations for redundant feature pruning. Experiments show that rankings learned by extracting more data from search trees for generating optimal training plans improve planner coverage. However, pairing with unsound pruning methods often results in diminishing performance, while our sound feature pruning methods provide consistent improvements across tested domains.

Details

ECAI Conference 2025 Conference Paper

Weisfeiler-Leman Features for Planning: A 1, 000, 000 Sample Size Hyperparameter Study

Dillon Z. Chen

Weisfeiler-Leman Features (WLFs) are a recently introduced classical machine learning tool for learning to plan and search. They have been shown to be both theoretically and empirically superior to existing deep learning approaches for learning value functions for search in symbolic planning. In this paper, we introduce new WLF hyperparameters and study their various tradeoffs and effects. We utilise the efficiency of WLFs and run planning experiments on single core CPUs with a sample size of 1, 000, 000 to understand the effect of hyperparameters on training and planning. Our experimental analysis show that there is a robust and best set of hyperparameters for WLFs across the tested planning domains. We find that the best WLF hyperparameters for learning heuristic functions minimise execution time rather than maximise model expressivity. We further statistically analyse and observe no significant correlation between training and planning metrics.

Details

NeurIPS Conference 2024 Conference Paper

Graph Learning for Numeric Planning

Dillon Z. Chen
Sylvie Thiébaux

Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary number of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance over domain-independent numeric planners.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Learning Domain-Independent Heuristics for Grounded and Lifted Planning

Dillon Z. Chen
Sylvie Thiébaux
Felipe Trevizan

We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular, to mitigate the issues caused by large grounded GNNs we present the first method for learning domain-independent heuristics with only the lifted representation of a planning task. We also provide a theoretical analysis of the expressiveness of our models, showing that some are more powerful than STRIPS-HGN, the only other existing model for learning domain-independent heuristics. Our experiments show that our heuristics generalise to much larger problems than those in the training set, vastly surpassing STRIPS-HGN heuristics.

PDF Details DOI

SoCS Conference 2024 Conference Paper

Novelty Heuristics, Multi-Queue Search, and Portfolios for Numeric Planning

Dillon Z. Chen
Sylvie Thiébaux

Heuristic search is a powerful approach for solving planning problems and numeric planning is no exception. In this paper, we boost the performance of heuristic search for numeric planning with various powerful techniques orthogonal to improving heuristic informedness: numeric novelty heuristics, the Manhattan distance heuristic, and exploring the use of multi-queue search and portfolios for combining heuristics.

Details

ICAPS Conference 2024 Conference Paper

Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning

Dillon Z. Chen
Felipe W. Trevizan
Sylvie Thiébaux

Current approaches for learning for planning have yet to achieve competitive performance against classical planners in several domains, and have poor overall performance. In this work, we construct novel graph representations of lifted planning tasks and use the WL algorithm to generate features from them. These features are used with classical machine learning methods which have up to 2 orders of magnitude fewer parameters and train up to 3 orders of magnitude faster than the state-of-the-art deep learning for planning models. Our novel approach, WL-GOOSE, reliably learns heuristics from scratch and outperforms the hFF heuristic in a fair competition setting. It also outperforms or ties with LAMA on 4 out of 10 domains on coverage and 7 out of 10 domains on plan quality. WL-GOOSE is the first learning for planning model which achieves these feats. Furthermore, we study the connections between our novel WL feature generation method, previous theoretically flavoured learning architectures, and Description Logic Features for planning.

Details

AAAI Conference 2023 Conference Paper

Heuristic Search for Multi-Objective Probabilistic Planning

Dillon Z. Chen
Felipe Trevizan
Sylvie Thiébaux

Heuristic search is a powerful approach that has successfully been applied to a broad class of planning problems, including classical planning, multi-objective planning, and probabilistic planning modelled as a stochastic shortest path (SSP) problem. Here, we extend the reach of heuristic search to a more expressive class of problems, namely multi-objective stochastic shortest paths (MOSSPs), which require computing a coverage set of non-dominated policies. We design new heuristic search algorithms MOLAO* and MOLRTDP, which extend well-known SSP algorithms to the multi-objective case. We further construct a spectrum of domain-independent heuristic functions differing in their ability to take into account the stochastic and multi-objective features of the problem to guide the search. Our experiments demonstrate the benefits of these algorithms and the relative merits of the heuristics.

PDF Details DOI

ICLR Conference 2023 Conference Paper

𝒩-WL: A New Hierarchy of Expressivity for Graph Neural Networks

Qing Wang 0002
Dillon Z. Chen
Asiri Wijesinghe
Shouheng Li
Muhammad Farhan

The expressive power of Graph Neural Networks (GNNs) is fundamental for understanding their capabilities and limitations, i.e., what graph properties can or cannot be learnt by a GNN. Since standard GNNs have been characterised to be upper-bounded by the Weisfeiler-Lehman (1-WL) algorithm, recent attempts concentrated on developing more expressive GNNs in terms of the $k$-WL hierarchy, a well-established framework for graph isormorphism tests. In this work we show that, contrary to the widely accepted view, the $k$-WL hierarchy is not well-suited for measuring expressive GNNs. This is due to limitations that are inherent to high-dimensional WL algorithms such as the lack of a natural interpretation and high computational costs, which makes it difficult to draw any firm conclusions about the expressive power of GNNs beyond 1-WL. Thus, we propose a novel hierarchy of graph isomorphism tests, namely Neighbourhood WL ($\mathscr{N}$-WL), and also establish a new theorem on the equivalence of expressivity between induced connected subgraphs and induced subgraphs within this hierarchy. Further, we design a GNN model upon $\mathscr{N}$-WL, Graph Neighbourhood Neural Network (G3N), and empirically verify its expressive power on synthetic and real-world benchmarks.

Details

ICAPS Conference 2022 Conference Paper

Flexible FOND HTN Planning: A Complexity Analysis

Dillon Z. Chen
Pascal Bercher

Hierarchical Task Network (HTN) planning is an expressive planning formalism that has often been advocated to address real-world problems. Yet few extensions exist that can deal with the many challenges encountered in the real world, one being the capability to express uncertainty. Recently, a new HTN formalism for fully observable nondeterministic problems was proposed and studied theoretically. In this paper, we lay out limitations of that formalism and propose an alternative definition, which addresses and resolves such limitations. We also study its complexity for certain problems.

Details

ICAPS Conference 2021 Conference Paper

Fully Observable Nondeterministic HTN Planning - Formalisation and Complexity Results

Dillon Z. Chen
Pascal Bercher

Much progress has been made in advancing the state of the art of HTN planning theory in recent years. However, scarce studies have been made with regards to the theory and complexity of HTN problems on nondeterministic domains. In this paper we provide a novel formalisation for fully observable nondeterministic HTN planning. We propose and study different solution criteria which differ in when nondeterministic action outcomes are considered: at plan generation or at plan execution. We integrate our solution criteria with notions of weak and strong plans canonical in nondeterministic planning and identify similarities and differences with plans in other fields of AI planning. We also provide completeness results for a majority of HTN problem subclasses and show the significant result that problems are not made any harder under nondeterminism for certain solution criteria by using compilation techniques to deterministic HTN planning. This supports and justifies the practicality and scalability of extending HTN problems over nondeterministic domains to deal with real world scenarios.

Details