# Differentiable Learning of Lifted Action Schemas for Classical Planning

arXiv: https://arxiv.org/abs/2605.13282 · HTML: https://mlsanity.com/paper/2605.13282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 13 May 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [Recurrent Independent Mechanisms](https://mlsanity.com/paper/1909.10893/) (2019)
- [Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary](https://mlsanity.com/paper/1705.00154/) (2017)
- [Learning First-Order Symbolic Representations for Planning from the Structure of the State Space](https://mlsanity.com/paper/1909.05546/) (2019)
- [Fast and Slow Learning of Recurrent Independent Mechanisms](https://mlsanity.com/paper/2105.08710/) (2021)
- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Classical Planning in Deep Latent Space](https://mlsanity.com/paper/2107.00110/) (2021)
- [Learning Transformer-based World Models with Contrastive Predictive Coding](https://mlsanity.com/paper/2503.04416/) (2025)
- [Transformers with Competitive Ensembles of Independent Mechanisms](https://mlsanity.com/paper/2103.00336/) (2021)
- [Safe Learning of Lifted Action Models](https://mlsanity.com/paper/2107.04169/) (2021)
- [Learning Lifted STRIPS Models from Action Traces Alone: A Simple, General, and Scalable Solution](https://mlsanity.com/paper/2411.14995/) (2024)
- [Planning Domain Model Acquisition from State Traces without Action Parameters](https://mlsanity.com/paper/2402.10726/) (2024)
- [Learning Lifted Action Models from Unsupervised Visual Traces](https://mlsanity.com/paper/2604.19043/) (2026)
- [Learning Lifted Action Models From Traces of Incomplete Actions and States](https://mlsanity.com/paper/2508.21449/) (2025)
- [From Next Token Prediction to (STRIPS) World Models](https://mlsanity.com/paper/2509.13389/) (2025)
- [Action Model Learning with Guarantees](https://mlsanity.com/paper/2404.09631/) (2024)

## Abstract (arXiv)

Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and relations, and lifted action schemas add or delete these atoms. This compact representation yields strong search heuristics and provides an ideal setting for structural generalization, since lifted relations and action schemas give rise to infinitely many domain instances. A central challenge is to learn these relations and action schemas from data, and recent approaches have addressed this problem using different types of observations. In this work, we develop a novel neural network architecture for learning action schemas from traces where states are fully observed but action arguments are unobserved. The problem is a simplification but an important step towards learning planning domains from sequences of images and action labels, and we aim to solve this simplification in a nearly perfect manner. The challenge lies in learning the action schemas while simultaneously identifying the action arguments from observed state changes. Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure. Additionally, we report experiments on robustness to observation noise and on a variation related to slot-based dynamics models.