← Back to papers
2025 L4DC L4DC 2025

Realizable Continuous-Space Shields for Safe Reinforcement Learning

Authors

KyungMin Kim , Davide Corsi , Andoni Rodrı́guez , JB Lanier , Benjami Parellada , Pierre Baldi , César Sánchez , Roy Fox
Download PDF

Related papers

Exploiting Approximate Symmetry for Efficient Multi-Agent Reinforcement Learning 2025
Learning Feasible Transitions for Efficient Contact Planning 2025
Learning Kolmogorov-Arnold Neural Activation Functions by Infinite-Dimensional Optimization 2025
A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning 2025
Safe Decision Transformer with Learning-based Constraints 2025