# Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces

arXiv: https://arxiv.org/abs/2410.12166 · HTML: https://mlsanity.com/paper/2410.12166/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 14 of 14)

- [Programmatically Interpretable Reinforcement Learning](https://mlsanity.com/paper/1804.02477/) (2018)
- [Verifiable Reinforcement Learning via Policy Extraction](https://mlsanity.com/paper/1805.08328/) (2018)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis](https://mlsanity.com/paper/1805.04276/) (2018)
- [Learning to Synthesize Programs as Interpretable and Generalizable Policies](https://mlsanity.com/paper/2108.13643/) (2021)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration](https://mlsanity.com/paper/2007.14381/) (2020)
- [Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs](https://mlsanity.com/paper/2301.12950/) (2023)
- [Just-in-Time Learning for Bottom-Up Enumerative Synthesis](https://mlsanity.com/paper/2010.08663/) (2020)
- [CrossBeam: Learning to Search in Bottom-Up Program Synthesis](https://mlsanity.com/paper/2203.10452/) (2022)
- [What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategies](https://mlsanity.com/paper/2203.11912/) (2022)
- [Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies](https://mlsanity.com/paper/2307.04893/) (2023)
- [Program Synthesis with Best-First Bottom-Up Search](https://mlsanity.com/paper/2310.04327/) (2023)
- [Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks](https://mlsanity.com/paper/2308.02729/) (2023)

## Built on by (most cited first, 2 of 2)

- [InnateCoder: Learning Programmatic Options with Foundation Models](https://mlsanity.com/paper/2505.12508/) (2025)
- [Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework](https://mlsanity.com/paper/2605.18454/) (2026)

## Abstract (arXiv)

Recent works have introduced LEAPS and HPRL, systems that learn latent spaces of domain-specific languages, which are used to define programmatic policies for partially observable Markov decision processes (POMDPs). These systems induce a latent space while optimizing losses such as the behavior loss, which aim to achieve locality in program behavior, meaning that vectors close in the latent space should correspond to similarly behaving programs. In this paper, we show that the programmatic space, induced by the domain-specific language and requiring no training, presents values for the behavior loss similar to those observed in latent spaces presented in previous work. Moreover, algorithms searching in the programmatic space significantly outperform those in LEAPS and HPRL. To explain our results, we measured the "friendliness" of the two spaces to local search algorithms. We discovered that algorithms are more likely to stop at local maxima when searching in the latent space than when searching in the programmatic space. This implies that the optimization topology of the programmatic space, induced by the reward function in conjunction with the neighborhood function, is more conducive to search than that of the latent space. This result provides an explanation for the superior performance in the programmatic space.