Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models

arXiv:2602.12444v2 Announce Type: replace Abstract: Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we introduce a novel recovery-based shielding fr...

🔗 Read more: https://arxiv.org/abs/2602.12444

#News #Software #Policy #Environment #Energy #Biology #Academic