# Learning General Policies from Small Examples Without Supervision

arXiv: https://arxiv.org/abs/2101.00692 · HTML: https://mlsanity.com/paper/2101.00692/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 3 Jan 2021.

## Builds on (most cited first, 9 of 9)

- [BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning](https://mlsanity.com/paper/1810.08272/) (2018)
- [Learning Generalized Reactive Policies using Deep Neural Networks](https://mlsanity.com/paper/1708.07280/) (2017)
- [Learning Features and Abstract Actions for Computing Generalized Plans](https://mlsanity.com/paper/1811.07231/) (2018)
- [Action Schema Networks: Generalised Policies with Deep Learning](https://mlsanity.com/paper/1709.04271/) (2017)
- [Few-Shot Bayesian Imitation Learning with Logical Program Policies](https://mlsanity.com/paper/1904.06317/) (2019)
- [Features, Projections, and Representation Change for Generalized Planning](https://mlsanity.com/paper/1801.10055/) (2018)
- [Qualitative Numeric Planning: Reductions and Complexity](https://mlsanity.com/paper/1912.04816/) (2019)
- [Generalized Planning With Procedural Domain Control Knowledge](https://mlsanity.com/paper/1910.04999/) (2019)
- [Symbolic Network: Generalized Neural Policies for Relational MDPs](https://mlsanity.com/paper/2002.07375/) (2020)

## Built on by (most cited first, 7 of 7)

- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Scaling-up Generalized Planning as Heuristic Search with Landmarks](https://mlsanity.com/paper/2205.04850/) (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)
- [Generalized Planning as Heuristic Search: A new planning search-space that leverages pointers over objects](https://mlsanity.com/paper/2301.11087/) (2023)
- [Representation and Synthesis of C++ Programs for Generalized Planning](https://mlsanity.com/paper/2206.14480/) (2022)
- [Revisiting Landmarks: Learning from Previous Plans to Generalize over Problem Instances](https://mlsanity.com/paper/2508.21564/) (2025)

## Abstract (arXiv)

Generalized planning is concerned with the computation of general policies that solve multiple instances of a planning domain all at once. It has been recently shown that these policies can be computed in two steps: first, a suitable abstraction in the form of a qualitative numerical planning problem (QNP) is learned from sample plans, then the general policies are obtained from the learned QNP using a planner. In this work, we introduce an alternative approach for computing more expressive general policies which does not require sample plans or a QNP planner. The new formulation is very simple and can be cast in terms that are more standard in machine learning: a large but finite pool of features is defined from the predicates in the planning examples using a general grammar, and a small subset of features is sought for separating "good" from "bad" state transitions, and goals from non-goals. The problems of finding such a "separating surface" while labeling the transitions as "good" or "bad" are jointly addressed as a single combinatorial optimization problem expressed as a Weighted Max-SAT problem. The advantage of looking for the simplest policy in the given feature space that solves the given examples, possibly non-optimally, is that many domains have no general, compact policies that are optimal. The approach yields general policies for a number of benchmark domains.