# HOUDINI: Lifelong Learning as Program Synthesis

arXiv: https://arxiv.org/abs/1804.00218 · HTML: https://mlsanity.com/paper/1804.00218/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2018.

## Built on by (most cited first, 30 of 38)

- [Modular Lifelong Reinforcement Learning via Neural Composition](https://mlsanity.com/paper/2207.00429/) (2022)
- [Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing](https://mlsanity.com/paper/2210.15889/) (2022)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Neural-guided, Bidirectional Program Search for Abstraction and Reasoning](https://mlsanity.com/paper/2110.11536/) (2021)
- [CompoSuite: A Compositional Reinforcement Learning Benchmark](https://mlsanity.com/paper/2207.04136/) (2022)
- [PyGlove: Symbolic Programming for Automated Machine Learning](https://mlsanity.com/paper/2101.08809/) (2021)
- [Pix2Code: Learning to Compose Neural Visual Concepts as Programs](https://mlsanity.com/paper/2402.08280/) (2024)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [Neurosymbolic Grounding for Compositional World Models](https://mlsanity.com/paper/2310.12690/) (2023)
- [Neurosymbolic Transformers for Multi-Agent Communication](https://mlsanity.com/paper/2101.03238/) (2021)
- [From Perception to Programs: Regularize, Overparameterize, and Amortize](https://mlsanity.com/paper/2206.05922/) (2022)
- [Self-explaining deep models with logic rule reasoning](https://mlsanity.com/paper/2210.07024/) (2022)
- [Discovering Design Concepts for CAD Sketches](https://mlsanity.com/paper/2210.14451/) (2022)
- [Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars](https://mlsanity.com/paper/2211.01842/) (2022)
- [Program Synthesis Guided Reinforcement Learning for Partially Observed Environments](https://mlsanity.com/paper/2102.11137/) (2021)
- [Unsupervised Learning of Neurosymbolic Encoders](https://mlsanity.com/paper/2107.13132/) (2021)
- [SEVerA: Verified Synthesis of Self-Evolving Agents](https://mlsanity.com/paper/2603.25111/) (2026)
- [SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries](https://mlsanity.com/paper/2206.13720/) (2022)
- [Neuro-Symbolic Learning: Principles and Applications in Ophthalmology](https://mlsanity.com/paper/2208.00374/) (2022)
- [Neurosymbolic Programming for Science](https://mlsanity.com/paper/2210.05050/) (2022)
- [The Need for Verification in AI-Driven Scientific Discovery](https://mlsanity.com/paper/2509.01398/) (2025)
- [Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis](https://mlsanity.com/paper/2111.15186/) (2021)
- [Efficient Non-Parametric Optimizer Search for Diverse Tasks](https://mlsanity.com/paper/2209.13575/) (2022)
- [Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction](https://mlsanity.com/paper/2405.15912/) (2024)
- [Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface](https://mlsanity.com/paper/2107.06393/) (2021)
- [Automated causal inference in application to randomized controlled clinical trials](https://mlsanity.com/paper/2201.05773/) (2022)
- [A Synergistic Approach In Network Intrusion Detection By Neurosymbolic AI](https://mlsanity.com/paper/2406.00938/) (2024)
- [Algorithmic Language Models with Neurally Compiled Libraries](https://mlsanity.com/paper/2407.04899/) (2024)
- [Interpreting Expert Annotation Differences in Animal Behavior](https://mlsanity.com/paper/2106.06114/) (2021)

## Abstract (arXiv)

We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing high-level concepts across domains and learning complex procedures are key challenges in lifelong learning. We show that a program synthesis approach that combines gradient descent with combinatorial search over programs can be a more effective response to these challenges than purely neural methods. Our framework, called HOUDINI, represents neural networks as strongly typed, differentiable functional programs that use symbolic higher-order combinators to compose a library of neural functions. Our learning algorithm consists of: (1) a symbolic program synthesizer that performs a type-directed search over parameterized programs, and decides on the library functions to reuse, and the architectures to combine them, while learning a sequence of tasks; and (2) a neural module that trains these programs using stochastic gradient descent. We evaluate HOUDINI on three benchmarks that combine perception with the algorithmic tasks of counting, summing, and shortest-path computation. Our experiments show that HOUDINI transfers high-level concepts more effectively than traditional transfer learning and progressive neural networks, and that the typed representation of networks significantly accelerates the search.