# muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults

arXiv: https://arxiv.org/abs/2408.15150 · HTML: https://mlsanity.com/paper/2408.15150/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2024.

## Built on by (most cited first, 5 of 5)

- [When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling](https://mlsanity.com/paper/2601.15232/) (2026)
- [Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests](https://mlsanity.com/paper/2601.04886/) (2026)
- [On Accelerating Deep Neural Network Mutation Analysis by Neuron and Mutant Clustering](https://mlsanity.com/paper/2501.12598/) (2025)
- [A Taxonomy of Runtime Faults in Model Context Protocol Servers](https://mlsanity.com/paper/2606.05339/) (2026)
- [Learning from the Test: Self-Referential Differential Testing for Deep RL Agents](https://mlsanity.com/paper/2608.22284/) (2026)

## Abstract (arXiv)

Reinforcement Learning (RL) is increasingly adopted to train agents that can deal with complex sequential tasks, such as driving an autonomous vehicle or controlling a humanoid robot. Correspondingly, novel approaches are needed to ensure that RL agents have been tested adequately before going to production. Among them, mutation testing is quite promising, especially under the assumption that the injected faults (mutations) mimic the real ones. In this paper, we first describe a taxonomy of real RL faults obtained by repository mining. Then, we present the mutation operators derived from such real faults and implemented in the tool muPRL. Finally, we discuss the experimental results, showing that muPRL is effective at discriminating strong from weak test generators, hence providing useful feedback to developers about the adequacy of the generated test scenarios.