# Learning Features and Abstract Actions for Computing Generalized Plans

arXiv: https://arxiv.org/abs/1811.07231 · HTML: https://mlsanity.com/paper/1811.07231/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2018.

## Built on by (most cited first, 30 of 35)

- [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021)
- [Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits](https://mlsanity.com/paper/2109.10129/) (2021)
- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Learning Generalized Policies Without Supervision Using GNNs](https://mlsanity.com/paper/2205.06002/) (2022)
- [Generalized Planning as Heuristic Search](https://mlsanity.com/paper/2103.14434/) (2021)
- [Scaling-up Generalized Planning as Heuristic Search with Landmarks](https://mlsanity.com/paper/2205.04850/) (2022)
- [Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width: Extended Version](https://mlsanity.com/paper/2203.14852/) (2022)
- [Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches: Extended Version](https://mlsanity.com/paper/2105.04250/) (2021)
- [PG3: Policy-Guided Planning for Generalized Policy Generation](https://mlsanity.com/paper/2204.10420/) (2022)
- [Learning General Policies from Small Examples Without Supervision](https://mlsanity.com/paper/2101.00692/) (2021)
- [Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems](https://mlsanity.com/paper/2204.12665/) (2022)
- [Symmetries and Expressive Requirements for Learning General Policies](https://mlsanity.com/paper/2409.15892/) (2024)
- [Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies](https://mlsanity.com/paper/2508.18507/) (2025)
- [Flexible FOND Planning with Explicit Fairness Assumptions](https://mlsanity.com/paper/2103.08391/) (2021)
- [BandMaxSAT: A Local Search MaxSAT Solver with Multi-armed Bandit](https://mlsanity.com/paper/2201.05544/) (2022)
- [Generalized Planning as Heuristic Search: A new planning search-space that leverages pointers over objects](https://mlsanity.com/paper/2301.11087/) (2023)
- [Farsighted Probabilistic Sampling: A General Strategy for Boosting Local Search MaxSAT Solvers](https://mlsanity.com/paper/2108.09988/) (2021)
- [First-Order Representation Languages for Goal-Conditioned RL](https://mlsanity.com/paper/2512.19355/) (2025)
- [Learning General Policies with Policy Gradient Methods](https://mlsanity.com/paper/2512.19366/) (2025)
- [Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems](https://mlsanity.com/paper/2204.04301/) (2022)
- [Learning First-Order Symbolic Planning Representations That Are Grounded](https://mlsanity.com/paper/2204.11902/) (2022)
- [Rethinking the Soft Conflict Pseudo Boolean Constraint on MaxSAT Local Search Solvers](https://mlsanity.com/paper/2401.10589/) (2024)
- [Sketch Decompositions for Classical Planning via Deep Reinforcement Learning](https://mlsanity.com/paper/2412.08574/) (2024)
- [Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Study](https://mlsanity.com/paper/2508.18515/) (2025)
- [Automatic Verification of Sound Abstractions for Generalized Planning](https://mlsanity.com/paper/2205.11898/) (2022)
- [Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains](https://mlsanity.com/paper/2404.02499/) (2024)
- [An Automatic Sound and Complete Abstraction Method for Generalized Planning with Baggable Types](https://mlsanity.com/paper/2501.15249/) (2025)
- [Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents](https://mlsanity.com/paper/2604.17019/) (2026)
- [Provably Complete Generalized Planning with LLMs](https://mlsanity.com/paper/2609.27105/) (2026)
- [Incorporating Multi-armed Bandit with Local Search for MaxSAT](https://mlsanity.com/paper/2211.16011/) (2022)

## Abstract (arXiv)

Generalized planning is concerned with the computation of plans that solve not one but multiple instances of a planning domain. Recently, it has been shown that generalized plans can be expressed as mappings of feature values into actions, and that they can often be computed with fully observable non-deterministic (FOND) planners. The actions in such plans, however, are not the actions in the instances themselves, which are not necessarily common to other instances, but abstract actions that are defined on a set of common features. The formulation assumes that the features and the abstract actions are given. In this work, we address this limitation by showing how to learn them automatically. The resulting account of generalized planning combines learning and planning in a novel way: a learner, based on a Max SAT formulation, yields the features and abstract actions from sampled state transitions, and a FOND planner uses this information, suitably transformed, to produce the general plans. Correctness guarantees are given and experimental results on several domains are reported.