# Common Benchmarks Undervalue the Generalization Power of Programmatic Policies

arXiv: https://arxiv.org/abs/2506.14162 · HTML: https://mlsanity.com/paper/2506.14162/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 17 Jun 2025.

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [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)
- [On the Practical Computational Power of Finite Precision RNNs for Language Recognition](https://mlsanity.com/paper/1805.04908/) (2018)
- [Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets](https://mlsanity.com/paper/1503.01007/) (2015)
- [Learning to Synthesize Programs as Interpretable and Generalizable Policies](https://mlsanity.com/paper/2108.13643/) (2021)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning](https://mlsanity.com/paper/2209.09203/) (2022)
- [babble: Learning Better Abstractions with E-Graphs and Anti-Unification](https://mlsanity.com/paper/2212.04596/) (2022)
- [MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning](https://mlsanity.com/paper/2312.15339/) (2023)
- [Bayesian Program Learning by Decompiling Amortized Knowledge](https://mlsanity.com/paper/2306.07856/) (2023)

## Abstract (arXiv)

Algorithms for learning programmatic representations for sequential decision-making problems are often evaluated on out-of-distribution (OOD) problems, with the common conclusion that programmatic policies generalize better than neural policies on OOD problems. In this position paper, we argue that commonly used benchmarks undervalue the generalization capabilities of programmatic representations. We analyze the experiments of four papers from the literature and show that neural policies, which were shown not to generalize, can generalize as effectively as programmatic policies on OOD problems. This is achieved with simple changes in the neural policies training pipeline. Namely, we show that simpler neural architectures with the same type of sparse observation used with programmatic policies can help attain OOD generalization. Another modification we have shown to be effective is the use of reward functions that allow for safer policies (e.g., agents that drive slowly can generalize better). Also, we argue for creating benchmark problems highlighting concepts needed for OOD generalization that may challenge neural policies but align with programmatic representations, such as tasks requiring algorithmic constructs like stacks.