Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications

arXiv:2404.09080v1 Announce Type: cross
Abstract: Integrating learning-based techniques, especially reinforcement learning, into robotics is promising for solving complex problems in unstructured environments. However, most existing approaches are trained in well-tuned simulators and subsequently deployed on real robots without online fine-tuning. In this setting, the simulation's realism seriously impacts the deployment's success rate. Instead, learning with real-world interaction data offers a promising alternative: not only eliminates the need for a fine-tuned simulator but also applies to a broader range of tasks …

applications arxiv cs.lg cs.ro manifold reinforcement reinforcement learning safe theory type