11 papers
Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning
Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen +1
We tackle the challenge of building embodied AI agents that can reliably solve long-horizon planning problems. Imitation learning from demonstrations has shown itself to be effecti…
Satisficing and Optimal Generalised Planning via Goal Regression (Extended Version)
Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen +1
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…
Symmetry-Invariant Novelty Heuristics via Unsupervised Weisfeiler-Leman Features
Dillon Z. Chen
Novelty heuristics aid heuristic search by exploring states that exhibit novel atoms. However, novelty heuristics are not symmetry invariant and hence may sometimes lead to redunda…
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 empiri…
Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
Dillon Z. Chen, Johannes Zenn, Tristan Cinquin +1
We study the usage of language models (LMs) for planning over world models specified in the Planning Domain Definition Language (PDDL). We prompt LMs to generate Python programs th…
Relational GNNs Cannot Learn Features for Planning
Dillon Z. Chen
Relational Graph Neural Networks (R-GNNs) are a GNN-based approach for learning value functions that can generalise to unseen problems from a given planning domain. R-GNNs were the…