# Learning Efficient Abstract Planning Models that Choose What to Predict arXiv: https://arxiv.org/abs/2208.07737 ยท HTML: https://mlsanity.com/paper/2208.07737/ ## Key facts - Cited by 17 papers in the map (data through 14 Oct 2026). - Builds on 21 of its 46 references that are in the map. - First posted on arXiv 16 Aug 2022. ## Builds on (most cited first, 21 of 21) - [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018) - [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020) - [BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments](https://mlsanity.com/paper/2108.03332/) (2021) - [A Compositional Object-Based Approach to Learning Physical Dynamics](https://mlsanity.com/paper/1612.00341/) (2016) - [Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary](https://mlsanity.com/paper/1705.00154/) (2017) - [Learning Symbolic Operators for Task and Motion Planning](https://mlsanity.com/paper/2103.00589/) (2021) - [Learning Neuro-Symbolic Skills for Bilevel Planning](https://mlsanity.com/paper/2206.10680/) (2022) - [Learning Plannable Representations with Causal InfoGAN](https://mlsanity.com/paper/1807.09341/) (2018) - [Learning Domain-Independent Planning Heuristics with Hypergraph Networks](https://mlsanity.com/paper/1911.13101/) (2019) - [Predicate Invention for Bilevel Planning](https://mlsanity.com/paper/2203.09634/) (2022) - [Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image](https://mlsanity.com/paper/2006.05398/) (2020) - [Learning compositional models of robot skills for task and motion planning](https://mlsanity.com/paper/2006.06444/) (2020) - [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021) - [Learning First-Order Symbolic Representations for Planning from the Structure of the State Space](https://mlsanity.com/paper/1909.05546/) (2019) - [Understanding the Power and Limitations of Teaching with Imperfect Knowledge](https://mlsanity.com/paper/2003.09712/) (2020) - [Combining Neural Networks and Tree Search for Task and Motion Planning in Challenging Environments](https://mlsanity.com/paper/1703.07887/) (2017) - [Discovering State and Action Abstractions for Generalized Task and Motion Planning](https://mlsanity.com/paper/2109.11082/) (2021) - [Generalized Lazy Search for Robot Motion Planning: Interleaving Search and Edge Evaluation via Event-based Toggles](https://mlsanity.com/paper/1904.02795/) (2019) - [Learning Partially Observable Deterministic Action Models](https://mlsanity.com/paper/1401.3437/) (2014) - [Learning STRIPS Action Models with Classical Planning](https://mlsanity.com/paper/1903.01153/) (2019) - [Active Learning of Abstract Plan Feasibility](https://mlsanity.com/paper/2107.00683/) (2021) ## Built on by (most cited first, 17 of 17) - [ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization](https://mlsanity.com/paper/2401.06949/) (2024) - [VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning](https://mlsanity.com/paper/2410.23156/) (2024) - [Practice Makes Perfect: Planning to Learn Skill Parameter Policies](https://mlsanity.com/paper/2402.15025/) (2024) - [Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness](https://mlsanity.com/paper/2403.10454/) (2024) - [Synthesizing world models for bilevel planning](https://mlsanity.com/paper/2503.20124/) (2025) - [From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models](https://mlsanity.com/paper/2501.00296/) (2024) - [Open-World Task and Motion Planning via Vision-Language Model Generated Constraints](https://mlsanity.com/paper/2411.08253/) (2024) - [ActionDiffusion: An Action-aware Diffusion Model for Procedure Planning in Instructional Videos](https://mlsanity.com/paper/2403.08591/) (2024) - [Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search](https://mlsanity.com/paper/2506.07062/) (2025) - [A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream](https://mlsanity.com/paper/2510.00182/) (2025) - [Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Acting](https://mlsanity.com/paper/2508.21501/) (2025) - [Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learning](https://mlsanity.com/paper/2409.19226/) (2024) - [Situationally-Aware Dynamics Learning](https://mlsanity.com/paper/2505.19574/) (2025) - [The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption](https://mlsanity.com/paper/2602.19260/) (2026) - [StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation](https://mlsanity.com/paper/2609.20791/) (2026) - [Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulation](https://mlsanity.com/paper/2604.03759/) (2026) - [Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints](https://mlsanity.com/paper/2606.06877/) (2026) ## Abstract (arXiv) An effective approach to solving long-horizon tasks in robotics domains with continuous state and action spaces is bilevel planning, wherein a high-level search over an abstraction of an environment is used to guide low-level decision-making. Recent work has shown how to enable such bilevel planning by learning abstract models in the form of symbolic operators and neural samplers. In this work, we show that existing symbolic operator learning approaches fall short in many robotics domains where a robot's actions tend to cause a large number of irrelevant changes in the abstract state. This is primarily because they attempt to learn operators that exactly predict all observed changes in the abstract state. To overcome this issue, we propose to learn operators that 'choose what to predict' by only modelling changes necessary for abstract planning to achieve specified goals. Experimentally, we show that our approach learns operators that lead to efficient planning across 10 different hybrid robotics domains, including 4 from the challenging BEHAVIOR-100 benchmark, while generalizing to novel initial states, goals, and objects.