Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees. (arXiv:2201.08355v1 [cs.RO])

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-to-Lab-to-Real to safely close the reality gap. To improve safety, we apply
a dual policy setup where a performance policy is trained using the cumulative
task reward and a backup (safety) policy is trained by …

arxiv lab learning reinforcement learning