paper-with-me

홈 › Papers

Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models

2026-05-14 · Senne Deproost, Denis Steckelmacher, Ann Nowé arxiv

Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off and select a fitting surrogate model. In addition to this, traditional distillation only minimizes the distance between the behavior of the original and the surrogate policy while other RL-specific components such as action value are disregarded. To solve this, we introduce a new model-agnostic method called Critic-Driven Voronoi State Partitioning, which partitions a black box control policy into regions where a simple class of model can be optimized using gradient descent. By exploiting the critic value network of the original policy, we iteratively introduce new subpolicies in regions with insufficient value, standing in for a measure of policy complexity. The partitioning, a Voronoi quantizer, uses nearest neighbor lookups to assign a linear function to each point in the state space resulting in a cell-like diagram. We validate our approach on several well known benchmarks and proof that this distillation approaches the original policy using a reasonable sized set of linear functions.

📄 PDF Abstract BibTeX arXiv:2605.14897

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies

2026-05-05 · Senne Deproost, Mehrdad Asadi, Ann Nowé arxiv

We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black box reinforcement learning policy using a set of human-interpretable subpolicies. By partitioning a distillation dataset of state actio…

Reinforcement Learning

Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning

2025-11-17 · Senne Deproost, Dennis Steckelmacher, Ann Nowé arxiv

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 w…

Reinforcement Learning

Semi-Discrete Normalizing Flows through Differentiable Tessellation

2022-03-14 · Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel

Mapping between discrete and continuous distributions is a difficult task and many have had to resort to heuristical approaches. We propose a tessellation-based approach that directly learns quantization boundaries in a …

Quantization

Text2voronoi: An Image-driven Approach to Differential Diagnosis

2016-08-01 · WS 2016 8 · Alex Mehler, er, Tolga Uslu, Wahed Hemati
Text Categorization

Geometry and clustering with metrics derived from separable Bregman divergences

2018-10-25 · Erika Gomes-Gonçalves, Henryk Gzyl, Frank Nielsen

Separable Bregman divergences induce Riemannian metric spaces that are isometric to the Euclidean space after monotone embeddings. We investigate fixed rate quantization and its codebook Voronoi diagrams, and report on e…

ClusteringQuantization