STACHE: Local Black-Box Explanations for Reinforcement Learning Policies
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909955223715840 |
|---|---|
| author | Elashkin, Andrew Grumberg, Orna |
| author_facet | Elashkin, Andrew Grumberg, Orna |
| contents | Reinforcement learning agents often behave unexpectedly in sparse-reward or safety-critical environments, creating a strong need for reliable debugging and verification tools. In this paper, we propose STACHE, a comprehensive framework for generating local, black-box explanations for an agent's specific action within discrete Markov games. Our method produces a Composite Explanation consisting of two complementary components: (1) a Robustness Region, the connected neighborhood of states where the agent's action remains invariant, and (2) Minimal Counterfactuals, the smallest state perturbations required to alter that decision. By exploiting the structure of factored state spaces, we introduce an exact, search-based algorithm that circumvents the fidelity gaps of surrogate models. Empirical validation on Gymnasium environments demonstrates that our framework not only explains policy actions, but also effectively captures the evolution of policy logic during training - from erratic, unstable behavior to optimized, robust strategies - providing actionable insights into agent sensitivity and decision boundaries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09909 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STACHE: Local Black-Box Explanations for Reinforcement Learning Policies Elashkin, Andrew Grumberg, Orna Machine Learning Artificial Intelligence 68T05, 68T20, 68Q60 I.2.6; I.2.8; F.1.1 Reinforcement learning agents often behave unexpectedly in sparse-reward or safety-critical environments, creating a strong need for reliable debugging and verification tools. In this paper, we propose STACHE, a comprehensive framework for generating local, black-box explanations for an agent's specific action within discrete Markov games. Our method produces a Composite Explanation consisting of two complementary components: (1) a Robustness Region, the connected neighborhood of states where the agent's action remains invariant, and (2) Minimal Counterfactuals, the smallest state perturbations required to alter that decision. By exploiting the structure of factored state spaces, we introduce an exact, search-based algorithm that circumvents the fidelity gaps of surrogate models. Empirical validation on Gymnasium environments demonstrates that our framework not only explains policy actions, but also effectively captures the evolution of policy logic during training - from erratic, unstable behavior to optimized, robust strategies - providing actionable insights into agent sensitivity and decision boundaries. |
| title | STACHE: Local Black-Box Explanations for Reinforcement Learning Policies |
| topic | Machine Learning Artificial Intelligence 68T05, 68T20, 68Q60 I.2.6; I.2.8; F.1.1 |
| url | https://arxiv.org/abs/2512.09909 |