English

Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation

Machine Learning 2026-03-11 v1 Artificial Intelligence

Abstract

Simulation-to-decision learning enables safe policy training in digital environments without risking real-world deployment, and has become essential in mission-critical domains such as supply chains and industrial systems. However, simulators learned from noisy or biased real-world data often exhibit prediction errors in decision-critical regions, leading to unstable action ranking and unreliable policies. Existing approaches either focus on improving average simulation fidelity or adopt conservative regularization, which may cause policy collapse by discarding high-risk high-reward actions. We propose Sim2Act, a robust simulation-to-decision framework that addresses both simulator and policy robustness. First, we introduce an adversarial calibration mechanism that re-weights simulation errors in decision-critical state-action pairs to align surrogate fidelity with downstream decision impact. Second, we develop a group-relative perturbation strategy that stabilizes policy learning under simulator uncertainty without enforcing overly pessimistic constraints. Extensive experiments on multiple supply chain benchmarks demonstrate improved simulation robustness and more stable decision performance under structured and unstructured perturbations.

Keywords

Cite

@article{arxiv.2603.09053,
  title  = {Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation},
  author = {Hongyu Cao and Jinghan Zhang and Kunpeng Liu and Dongjie Wang and Feng Xia and Haifeng Chen and Xiaohua Hu and Yanjie Fu},
  journal= {arXiv preprint arXiv:2603.09053},
  year   = {2026}
}

Comments

9 pages, 5 figures

R2 v1 2026-07-01T11:11:27.340Z