Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.20660 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913762145992704 |
|---|---|
| author | Jesawada, Hozefa Acernese, Antonio Russo, Giovanni Del Vecchio, Carmen |
| author_facet | Jesawada, Hozefa Acernese, Antonio Russo, Giovanni Del Vecchio, Carmen |
| contents | Ensuring robustness against epistemic, possibly adversarial, perturbations is essential for reliable real-world decision-making. While the Probabilistic Ensembles with Trajectory Sampling (PETS) algorithm inherently handles uncertainty via ensemble-based probabilistic models, it lacks guarantees against structured adversarial or worst-case uncertainty distributions. To address this, we propose DR-PETS, a distributionally robust extension of PETS that certifies robustness against adversarial perturbations. We formalize uncertainty via a p-Wasserstein ambiguity set, enabling worst-case-aware planning through a min-max optimization framework. While PETS passively accounts for stochasticity, DR-PETS actively optimizes robustness via a tractable convex approximation integrated into PETS planning loop. Experiments on pendulum stabilization and cart-pole balancing show that DR-PETS certifies robustness against adversarial parameter perturbations, achieving consistent performance in worst-case scenarios where PETS deteriorates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20660 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DR-PETS: Learning-Based Control With Planning in Adversarial Environments Jesawada, Hozefa Acernese, Antonio Russo, Giovanni Del Vecchio, Carmen Machine Learning Optimization and Control Ensuring robustness against epistemic, possibly adversarial, perturbations is essential for reliable real-world decision-making. While the Probabilistic Ensembles with Trajectory Sampling (PETS) algorithm inherently handles uncertainty via ensemble-based probabilistic models, it lacks guarantees against structured adversarial or worst-case uncertainty distributions. To address this, we propose DR-PETS, a distributionally robust extension of PETS that certifies robustness against adversarial perturbations. We formalize uncertainty via a p-Wasserstein ambiguity set, enabling worst-case-aware planning through a min-max optimization framework. While PETS passively accounts for stochasticity, DR-PETS actively optimizes robustness via a tractable convex approximation integrated into PETS planning loop. Experiments on pendulum stabilization and cart-pole balancing show that DR-PETS certifies robustness against adversarial parameter perturbations, achieving consistent performance in worst-case scenarios where PETS deteriorates. |
| title | DR-PETS: Learning-Based Control With Planning in Adversarial Environments |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2503.20660 |