# Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies

arXiv: https://arxiv.org/abs/2409.10218 · HTML: https://mlsanity.com/paper/2409.10218/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 9 of 9)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [Omega-Regular Objectives in Model-Free Reinforcement Learning](https://mlsanity.com/paper/1810.00950/) (2018)
- [The Probabilistic Model Checker Storm](https://mlsanity.com/paper/2002.07080/) (2020)
- [Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)](https://mlsanity.com/paper/2112.15422/) (2021)
- [Verification of Markov Decision Processes using Learning Algorithms](https://mlsanity.com/paper/1402.2967/) (2014)
- [COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking](https://mlsanity.com/paper/2209.07133/) (2022)
- [Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learning](https://mlsanity.com/paper/2004.00273/) (2020)
- [Probabilistic Model Checking of Stochastic Reinforcement Learning Policies](https://mlsanity.com/paper/2403.18725/) (2024)

## Built on by (most cited first, 9 of 9)

- [Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC](https://mlsanity.com/paper/2602.14505/) (2026)
- [Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies](https://mlsanity.com/paper/2501.03142/) (2025)
- [Verifying Memoryless Sequential Decision-making of Large Language Models](https://mlsanity.com/paper/2510.06756/) (2025)
- [Formal Verification of Noisy Quantum Reinforcement Learning Policies](https://mlsanity.com/paper/2512.01502/) (2025)
- [Translating the Rashomon Effect to Sequential Decision-Making Tasks](https://mlsanity.com/paper/2512.17470/) (2025)
- [COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management](https://mlsanity.com/paper/2603.02396/) (2026)
- [COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance](https://mlsanity.com/paper/2603.07546/) (2026)
- [Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation](https://mlsanity.com/paper/2606.19632/) (2026)
- [Probabilistic Model Checking of Autoregressive Neural Sequence Models](https://mlsanity.com/paper/2609.00838/) (2026)

## Abstract (arXiv)

Pruning neural networks (NNs) can streamline them but risks removing vital parameters from safe reinforcement learning (RL) policies. We introduce an interpretable RL method called VERINTER, which combines NN pruning with model checking to ensure interpretable RL safety. VERINTER exactly quantifies the effects of pruning and the impact of neural connections on complex safety properties by analyzing changes in safety measurements. This method maintains safety in pruned RL policies and enhances understanding of their safety dynamics, which has proven effective in multiple RL settings.