Search papers, labs, and topics across Lattice.
The paper introduces Sim2Act, a framework for robust simulation-to-decision learning that tackles prediction errors in decision-critical regions of simulators. It uses adversarial calibration to re-weight simulation errors based on their impact on downstream decisions and employs a group-relative perturbation strategy to stabilize policy learning under simulator uncertainty. Experiments on supply chain benchmarks show that Sim2Act improves simulation robustness and decision performance under various perturbations.
Stop letting simulator errors in critical regions derail your policies: Sim2Act aligns surrogate fidelity with downstream decision impact, leading to more stable and robust decision-making.
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.
