# Translating the Rashomon Effect to Sequential Decision-Making Tasks

arXiv: https://arxiv.org/abs/2512.17470 · HTML: https://mlsanity.com/paper/2512.17470/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [On the Existence of Simpler Machine Learning Models](https://mlsanity.com/paper/1908.01755/) (2019)
- [When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?](https://mlsanity.com/paper/2204.05618/) (2022)
- [Exploring the Whole Rashomon Set of Sparse Decision Trees](https://mlsanity.com/paper/2209.08040/) (2022)
- [The Probabilistic Model Checker Storm](https://mlsanity.com/paper/2002.07080/) (2020)
- [An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning](https://mlsanity.com/paper/2306.15786/) (2023)
- [COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking](https://mlsanity.com/paper/2209.07133/) (2022)
- [Permissive Controller Synthesis for Probabilistic Systems](https://mlsanity.com/paper/1504.04662/) (2015)
- [Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set](https://mlsanity.com/paper/2110.13369/) (2021)
- [Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies](https://mlsanity.com/paper/2409.10218/) (2024)
- [Robustness Verification for Classifier Ensembles](https://mlsanity.com/paper/2005.05587/) (2020)
- [Rashomon in the Streets: Explanation Ambiguity in Scene Understanding](https://mlsanity.com/paper/2509.03169/) (2025)

## Abstract (arXiv)

The Rashomon effect describes the phenomenon where multiple models trained on the same data produce identical predictions while differing in which features they rely on internally. This effect has been studied extensively in classification tasks, but not in sequential decision-making, where an agent learns a policy to achieve an objective by taking actions in an environment. In this paper, we translate the Rashomon effect to sequential decision-making. We define it as multiple policies that exhibit identical behavior, visiting the same states and selecting the same actions, while differing in their internal structure, such as feature attributions. Verifying identical behavior in sequential decision-making differs from classification. In classification, predictions can be directly compared to ground-truth labels. In sequential decision-making with stochastic transitions, the same policy may succeed or fail on any single trajectory due to randomness. We address this using formal verification methods that construct and compare the complete probabilistic behavior of each policy in the environment. Our experiments demonstrate that the Rashomon effect exists in sequential decision-making. We further show that ensembles constructed from the Rashomon set exhibit greater robustness to distribution shifts than individual policies. Additionally, permissive policies derived from the Rashomon set reduce computational requirements for verification while maintaining optimal performance.