# Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments

arXiv: https://arxiv.org/abs/2510.19244 · HTML: https://mlsanity.com/paper/2510.19244/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- Deep reinforcement learning methods / [Interpretable and logic-guided RL](https://mlsanity.com/deeprl/interpretable-and-logic-guided-rl/)

## Builds on (most cited first, 17 of 17)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [Visualizing and Understanding Atari Agents](https://mlsanity.com/paper/1711.00138/) (2017)
- [Shapley explainability on the data manifold](https://mlsanity.com/paper/2006.01272/) (2020)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [Interpretable Policies for Reinforcement Learning by Genetic Programming](https://mlsanity.com/paper/1712.04170/) (2017)
- [Vision-Language Models Provide Promptable Representations for Reinforcement Learning](https://mlsanity.com/paper/2402.02651/) (2024)
- [Explaining Reinforcement Learning with Shapley Values](https://mlsanity.com/paper/2306.05810/) (2023)
- [Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions](https://mlsanity.com/paper/2406.04606/) (2024)
- [Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers](https://mlsanity.com/paper/2403.11907/) (2024)
- [Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs](https://mlsanity.com/paper/2503.08322/) (2025)
- [From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation](https://mlsanity.com/paper/2501.09858/) (2025)
- [A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values](https://mlsanity.com/paper/2505.07797/) (2025)
- [Surrogate Fitness Metrics for Interpretable Reinforcement Learning](https://mlsanity.com/paper/2504.14645/) (2025)
- [Counterfactual Explanations for Continuous Action Reinforcement Learning](https://mlsanity.com/paper/2505.12701/) (2025)

## Built on by (most cited first, 1 of 1)

- [Automated Testing of LLM-Based Post Hoc Explainers Using Model Checking as an Oracle](https://mlsanity.com/paper/2608.30581/) (2026)

## Abstract (arXiv)

Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior. The existing SILVER framework (Li, Siddique, and Cao 2025) explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains. We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action and high-dimensional environments by incorporating the RL policy's own action outputs into the boundary points identification. Our method first extracts compact feature representations from image observations, performs SHAP-based feature attribution, and then employs RL-guided labeling to generate behaviorally consistent boundary datasets. Surrogate models, such as decision trees and regression-based functions, are subsequently trained to interpret RL policy's decision structure. We evaluate the proposed framework on two Atari environments using three deep RL algorithms and conduct human-subject study to assess the clarity and trustworthiness of the derived interpretable policy. Results show that our approach maintains competitive task performance while substantially improving transparency and human understanding of agent behavior. This work advances explainable RL by transforming SILVER into a scalable and behavior-aware framework for interpreting deep RL agents in high-dimensional, multi-action settings.