{"ID":2840580,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.13322","arxiv_id":"2511.13322","title":"Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning","abstract":"Deep Reinforcement Learning is one of the state-of-the-art methods for producing near-optimal system controllers. However, deep RL algorithms train a deep neural network, that lacks transparency, which poses challenges when the controller has to meet regulations, or foster trust. To alleviate this, one could transfer the learned behaviour into a model that is human-readable by design using knowledge distilla- tion. Often this is done with a single model which mimics the original model on average but could struggle in more dynamic situations. A key challenge is that this simpler model should have the right balance be- tween flexibility and complexity or right balance between balance bias and accuracy. We propose a new model-agnostic method to divide the state space into regions where a simplified, human-understandable model can operate in. In this paper, we use Voronoi partitioning to find regions where linear models can achieve similar performance to the original con- troller. We evaluate our approach on a gridworld environment and a classic control task. We observe that our proposed distillation to locally- specialized linear models produces policies that are explainable and show that the distillation matches or even slightly outperforms the black-box policy they are distilled from.","short_abstract":"Deep Reinforcement Learning is one of the state-of-the-art methods for producing near-optimal system controllers. However, deep RL algorithms train a deep neural network, that lacks transparency, which poses challenges when the controller has to meet regulations, or foster trust. To alleviate this, one could transfer t...","url_abs":"https://arxiv.org/abs/2511.13322","url_pdf":"https://arxiv.org/pdf/2511.13322v1","authors":"[\"Senne Deproost\",\"Dennis Steckelmacher\",\"Ann Nowé\"]","published":"2025-11-17T12:58:38Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}