# Deep Learning for Generalised Planning with Background Knowledge

arXiv: https://arxiv.org/abs/2410.07923 · HTML: https://mlsanity.com/paper/2410.07923/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 21 of 21)

- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [Neural Logic Machines](https://mlsanity.com/paper/1904.11694/) (2019)
- [The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks](https://mlsanity.com/paper/1401.3839/) (2014)
- [Learning Domain-Independent Planning Heuristics with Hypergraph Networks](https://mlsanity.com/paper/1911.13101/) (2019)
- [Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits](https://mlsanity.com/paper/2109.10129/) (2021)
- [Learning Domain-Independent Heuristics for Grounded and Lifted Planning](https://mlsanity.com/paper/2312.11143/) (2023)
- [Features, Projections, and Representation Change for Generalized Planning](https://mlsanity.com/paper/1801.10055/) (2018)
- [Learning to Rank for Synthesizing Planning Heuristics](https://mlsanity.com/paper/1608.01302/) (2016)
- [Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning](https://mlsanity.com/paper/2007.06702/) (2020)
- [Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning](https://mlsanity.com/paper/2403.16508/) (2024)
- [Qualitative Numeric Planning: Reductions and Complexity](https://mlsanity.com/paper/1912.04816/) (2019)
- [Generalized Planning as Heuristic Search](https://mlsanity.com/paper/2103.14434/) (2021)
- [Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach](https://mlsanity.com/paper/2304.08349/) (2023)
- [Scaling-up Generalized Planning as Heuristic Search with Landmarks](https://mlsanity.com/paper/2205.04850/) (2022)
- [Blocks: Collaborative and Persistent Augmented Reality Experiences](https://mlsanity.com/paper/1908.02409/) (2019)
- [Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal](https://mlsanity.com/paper/2310.19463/) (2023)
- [Beyond Graph Neural Networks with Lifted Relational Neural Networks](https://mlsanity.com/paper/2007.06286/) (2020)
- [Levin Tree Search with Context Models](https://mlsanity.com/paper/2305.16945/) (2023)
- [Hierarchical Decomposition and Analysis for Generalized Planning](https://mlsanity.com/paper/2212.02823/) (2022)
- [Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains](https://mlsanity.com/paper/2404.02499/) (2024)

## Built on by (most cited first, 2 of 2)

- [Graph Learning for Numeric Planning](https://mlsanity.com/paper/2410.24080/) (2024)
- [Graph Learning for Planning: The Story Thus Far and Open Challenges](https://mlsanity.com/paper/2412.02136/) (2024)

## Abstract (arXiv)

Automated planning is a form of declarative problem solving which has recently drawn attention from the machine learning (ML) community. ML has been applied to planning either as a way to test `reasoning capabilities' of architectures, or more pragmatically in an attempt to scale up solvers with learned domain knowledge. In practice, planning problems are easy to solve but hard to optimise. However, ML approaches still struggle to solve many problems that are often easy for both humans and classical planners. In this paper, we thus propose a new ML approach that allows users to specify background knowledge (BK) through Datalog rules to guide both the learning and planning processes in an integrated fashion. By incorporating BK, our approach bypasses the need to relearn how to solve problems from scratch and instead focuses the learning on plan quality optimisation. Experiments with BK demonstrate that our method successfully scales and learns to plan efficiently with high quality solutions from small training data generated in under 5 seconds.