2024
Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees (Abstract Reprint)
AAAI 2024technical
Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world. In particular, policies learned using reinforcement learning often fail to generalize to novel environments due to unsafe behavior. In this paper, we propose Sim…