arXiv:2609.13044v2 cs.LG

Robust Policy Optimization via Adversarial Importance Sampling

Amine Andam, Jamal Bentahar, Mustapha Hedabou

제출 2026-11-05

원문 초록

Significant progress has been made in safeguarding Deep Reinforcement Learning (DRL) policies against input perturbations. Developing robust DRL involves three main stages: algorithm design, implementation, and evaluation. In this work, we identify and address a key limitation at each stage. First, we introduce Adversarial Importance Sampling (Advis), a method that estimates and optimizes worst-case returns directly from trajectories already collected during standard training. Advis satisfies three desirable criteria that prior work does not jointly achieve: it requires no additional environment interactions, no auxiliary networks, and captures long-term robustness. Second, we introduce advrl, a modular PyTorch library that provides clean, single-file implementations of existing robustness methods and adversarial attacks, enabling rapid prototyping and reproducible evaluations. Third, we revisit evaluation under learned adversaries and show that optimal adversarial hyperparameters do not transfer across agents, which can lead to an overestimation of robustness when using a limited set of attacker configurations. Accordingly, we evaluate policies against a large and diverse set of attackers, using 6 to 14 times more configurations than prior work. Finally, experiments on continuous control environments show that Advis achieves stronger worst-case performance and greater training efficiency than existing baselines.

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2609.13044v2제출 시각 미확인

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.