Sim-to-Lab-to-Real: Safe reinforcement learning with shielding and generalization guarantees

2022/10/26 by Kai-Chieh Hsu, Kai–Chieh Hsu, Allen Z. Ren +3 · 33 citations
Computer Science · Engineering · Mathematics · #Adversarial Robustness in Machine Learning #Artificial intelligence #Backup #Computer science #Database #Generalization #Leverage (statistics) #Machine learning #Mathematics #Reachability #Reinforcement Learning in Robotics #Reinforcement learning #Robot Manipulation and Learning #Theoretical computer science

paper · doi:10.1016/j.artint.2022.103811

published in Artificial Intelligence 314, 103811 (Elsevier BV)

openalex publication_date 2022/10/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Cited by

• RoboBPP: Benchmarking Robotic Online Bin Packing with Physics-based Simulation
• How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints
• Reachable Predictive Control: A Novel Control Algorithm for Nonlinear Systems with Unknown Dynamics and its Practical Applications
• AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Space
• SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer
• Advances, challenges, and opportunities for legged robots
• LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
• A Provable Approach for End-to-End Safe Reinforcement Learning
• Deep Actor-Critics with Tight Risk Certificates
• Guided by Guardrails: Control Barrier Functions as Safety Instructors for Robotic Learning
• Solving Reach- and Stabilize-Avoid Problems Using Discounted Reachability
• Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures
• Neural Fidelity Calibration for Informative Sim-to-Real Adaptation
• Multi-robot hierarchical safe reinforcement learning autonomous decision-making strategy based on uniformly ultimate boundedness constraints. [europepmc]