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

• URL: http://arxiv.org/abs/2603.09053v1
• Date: Tue, 10 Mar 2026 00:51:47 GMT
• Title: Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation
• Abstract summary: Simulation-to-decision learning enables safe policy training in digital environments without risking real-world deployment.<n>Existing approaches either focus on improving average simulation fidelity or adopt conservative regularization.<n>We propose Sim2Act, a robust simulation-to-decision framework that addresses both simulator and policy robustness.
• Score: 54.29523408543184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Robust Control under Stationary Ambiguity [5.394466899760558]
  Control policies optimized in simulation can perform poorly in the real system when the parameters of the simulator are estimated from limited data.<n>We propose training policies in simulators where ambiguity varies with the system's state but does not systematically decay over time.<n>We show how to construct such simulators and demonstrate, on hedging problems, that policies trained under stationary ambiguity preserve robustness to latent factors over time.
  arXiv  Detail & Related papers  (2026-08-05T13:34:00Z)
• From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving [56.30087557121323]
  AlignADV is a learnability-guided closed-loop adversarial training framework.<n>It converts adversarial scenarios into resolvable and capability-aligned curricula.<n> Experiments show it reduces training steps by up to 40.6 percent.
  arXiv  Detail & Related papers  (2026-06-12T02:13:55Z)
• A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation [13.439555106885491]
  We study whether simulated evaluation preserves real-world conclusions in terms of policy ranking consistency, performance correlation, and perturbation-wise failure patterns.<n>This analysis allows us to characterize the limitations of existing simulators and identify what kinds of simulation signals are more aligned with real-world deployment.
  arXiv  Detail & Related papers  (2026-06-09T03:25:02Z)
• On the Plasticity and Stability for Post-Training Large Language Models [54.757672540381236]
  We identify a root cause as the conflict between plasticity and stability gradients.<n>We propose Probabilistic Conflict Resolution (PCR), a framework that models gradients as random variables.<n>PCR significantly smooths the training trajectory and achieves superior performance in various reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-06T07:31:26Z)
• ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation [72.78362530982109]
  ARTIS, Agentic Risk-Aware Test-Time Scaling via Iterative Simulation, is a framework that decouples exploration from commitment.<n>We show that naive LLM-based simulators struggle to capture rare but high-impact failure modes.<n>We introduce a risk-aware tool simulator that emphasizes fidelity on failure-inducing actions.
  arXiv  Detail & Related papers  (2026-02-02T06:33:22Z)
• Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators [9.868826622074899]
  SureSim is a framework to augment large-scale simulation with relatively small-scale real-world testing.<n>We leverage non-asymptotic mean estimation algorithms to provide confidence intervals on mean policy performance.<n>Our approach saves over (20-25%) of hardware evaluation effort to achieve similar bounds on policy performance.
  arXiv  Detail & Related papers  (2025-10-05T20:37:53Z)
• Supply Chain Optimization via Generative Simulation and Iterative Decision Policies [39.67447490193419]
  Sim-to-Dec is a framework combining an efficient simulator with an intelligent decision-making algorithm.<n>Experiments conducted on three real-world datasets demonstrate that Sim-to-Dec significantly improves timely delivery rates and profit.
  arXiv  Detail & Related papers  (2025-07-10T00:41:15Z)
• Neural Fidelity Calibration for Informative Sim-to-Real Adaptation [10.117298045153564]
  Deep reinforcement learning can seamlessly transfer agile locomotion and navigation skills from the simulator to real world.<n>However, bridging the sim-to-real gap with domain randomization or adversarial methods often demands expert physics knowledge to ensure policy robustness.<n>We propose Neural Fidelity (NFC), a novel framework that employs conditional score-based diffusion models to calibrate simulator physical coefficients and residual fidelity domains online during robot execution.
  arXiv  Detail & Related papers  (2025-04-11T15:12:12Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Analyzing and Enhancing Closed-loop Stability in Reactive Simulation [25.27603440925488]
  We propose a new reactive simulation framework to bridge the human behavior gap between simulation and real-world traffic scenarios. We first propose a new reactive simulation framework, where the smoothness and consistency of the simulated state sequences are crucial factors to stability. We then incorporate the kinematic vehicle model into the framework to improve the closed-loop stability of the reactive simulation.
  arXiv  Detail & Related papers  (2022-08-09T06:31:35Z)
• ERMAS: Becoming Robust to Reward Function Sim-to-Real Gaps in Multi-Agent Simulations [110.72725220033983]
  Epsilon-Robust Multi-Agent Simulation (ERMAS) is a framework for learning AI policies that are robust to such multiagent sim-to-real gaps. ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations. In particular, ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations.
  arXiv  Detail & Related papers  (2021-06-10T04:32:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.