Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908847501737984 |
|---|---|
| author | Ubukata, Toshihide Wang, Zhiyao Mu, Enhong Li, Jialong Tei, Kenji |
| author_facet | Ubukata, Toshihide Wang, Zhiyao Mu, Enhong Li, Jialong Tei, Kenji |
| contents | On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement learning (RL) approaches learn such policies and achieve promising zero-shot generalization from small training instances to larger unseen ones. However, a fundamental limitation is anisotropic generalization, where an RL policy exhibits strong performance only in a specific region of the domain-parameter space while remaining fragile elsewhere due to training stochasticity and trajectory-dependent bias. To address this, we propose a Soft Mixture-of-Experts framework that combines multiple RL experts via a prior-confidence gating mechanism and treats these anisotropic behaviors as complementary specializations. The evaluation on the Air Traffic benchmark shows that Soft-MoE substantially expands the solvable parameter space and improves robustness compared to any single expert. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19244 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts Ubukata, Toshihide Wang, Zhiyao Mu, Enhong Li, Jialong Tei, Kenji Artificial Intelligence Machine Learning On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement learning (RL) approaches learn such policies and achieve promising zero-shot generalization from small training instances to larger unseen ones. However, a fundamental limitation is anisotropic generalization, where an RL policy exhibits strong performance only in a specific region of the domain-parameter space while remaining fragile elsewhere due to training stochasticity and trajectory-dependent bias. To address this, we propose a Soft Mixture-of-Experts framework that combines multiple RL experts via a prior-confidence gating mechanism and treats these anisotropic behaviors as complementary specializations. The evaluation on the Air Traffic benchmark shows that Soft-MoE substantially expands the solvable parameter space and improves robustness compared to any single expert. |
| title | Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.19244 |