Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913130345398272 |
|---|---|
| author | Deproost, Senne Asadi, Mehrdad Nowé, Ann |
| author_facet | Deproost, Senne Asadi, Mehrdad Nowé, Ann |
| contents | 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 action pairs with linear support vector machine splits, SVSP constructs a compact and structured representation of the original policy. Our method improves mean return by +7.4% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1%. Our results pave the path towards a more flexible form of distillation where both the decision boundary and surrogate models can be chosen within a margin of the original black box behavior. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04254 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies Deproost, Senne Asadi, Mehrdad Nowé, Ann Machine Learning Human-Computer Interaction 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 action pairs with linear support vector machine splits, SVSP constructs a compact and structured representation of the original policy. Our method improves mean return by +7.4% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1%. Our results pave the path towards a more flexible form of distillation where both the decision boundary and surrogate models can be chosen within a margin of the original black box behavior. |
| title | Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies |
| topic | Machine Learning Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.04254 |