LyEvO: Lyapunov-Guided Evolutionary Optimization for Safe and Robust Sim-to-Real Policy Learning

• URL: http://arxiv.org/abs/2608.06481v1
• Date: Thu, 06 Aug 2026 18:19:33 GMT
• Title: LyEvO: Lyapunov-Guided Evolutionary Optimization for Safe and Robust Sim-to-Real Policy Learning
• Abstract summary: Training controllers that are safe and robust in simulation, and systematically assessing their readiness for real-world deployment, remain key challenges in sim-to-real transfer.<n>We propose LyEvO, a physics-grounded framework that combines constrained Evolutionary Optimization and Statistical Model Checking (SMC)-based verification with Lyapunov-based stability analysis.<n>We evaluate LyEvO on Cartpole and 3D Quadrotor benchmarks through extensive simulations and targeted real-world experiments, demonstrating safe and robust sim-to-real transfer.
• Score: 4.6279005223541105
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training controllers that are safe and robust in simulation, and systematically assessing their readiness for real-world deployment, remain key challenges in sim-to-real transfer. To address this, we propose LyEvO, a physics-grounded framework that combines constrained Evolutionary Optimization and Statistical Model Checking (SMC)-based verification with Lyapunov-based stability analysis. Leveraging prior knowledge of the system dynamics, LyEvO uses Lyapunov analysis to compute an initial candidate stability region. An iterative loop then uses operational scenarios drawn from this region to jointly optimize and statistically verify a policy, and subsequently expands the region's boundaries based on the verification outcome. This integrated procedure provides a practical criterion for assessing deployment readiness. We evaluate LyEvO on Cartpole and 3D Quadrotor benchmarks through extensive simulations and targeted real-world experiments, demonstrating safe and robust sim-to-real transfer.

Related papers

• 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)
• Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation [54.29523408543184]
  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.
  arXiv  Detail & Related papers  (2026-03-10T00:51:47Z)
• Stabilizing Policy Optimization via Logits Convexity [59.242732612484474]
  We show that the convexity of the supervised fine-tuning loss with respect to model logits plays a key role in enabling stable training.<n>Motivated by this observation, we propose Logits Convex Optimization (LCO), a simple yet effective policy optimization framework.
  arXiv  Detail & Related papers  (2026-03-01T07:40:12Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• 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)
• Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling [84.00480999255628]
  Reinforcement Learning algorithms for safety alignment of Large Language Models (LLMs) encounter the challenge of distribution shift.<n>Current approaches typically address this issue through online sampling from the target policy.<n>We propose a new framework that leverages the model's intrinsic safety judgment capability to extract reward signals.
  arXiv  Detail & Related papers  (2025-03-13T06:40:34Z)
• LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots [20.715834172041763]
  We propose LoopSR, a lifelong policy adaptation framework that continuously refines RL policies in the post-deployment stage.<n>LoopSR employs a transformer-based encoder to map real-world trajectories into a latent space.<n>Autoencoder architecture and contrastive learning methods are adopted to enhance feature extraction of real-world dynamics.
  arXiv  Detail & Related papers  (2024-09-26T16:02:25Z)
• 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)
• Gaussian Process-based Min-norm Stabilizing Controller for Control-Affine Systems with Uncertain Input Effects and Dynamics [90.81186513537777]
  We propose a novel compound kernel that captures the control-affine nature of the problem. We show that this resulting optimization problem is convex, and we call it Gaussian Process-based Control Lyapunov Function Second-Order Cone Program (GP-CLF-SOCP)
  arXiv  Detail & Related papers  (2020-11-14T01:27:32Z)

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.