Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation
This addresses robust policy training for mission-critical domains like supply chains, but it appears incremental as it builds on existing simulation-to-decision methods.
The paper tackled the problem of simulation-to-decision learning, where simulators from noisy data cause unstable policies, by proposing Sim2Act with adversarial calibration and group-relative perturbation, resulting in improved simulation robustness and stable decision performance in supply chain benchmarks.
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.