Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models. (arXiv:2205.05787v1 [cs.RO])

Bridging model-based safety and model-free reinforcement learning (RL) for
dynamic robots is appealing since model-based methods are able to provide
formal safety guarantees, while RL-based methods are able to exploit the robot
agility by learning from the full-order system dynamics. However, current
approaches to tackle this problem are mostly restricted to simple systems. In
this paper, we propose a new method to combine model-based safety with
model-free reinforcement learning by explicitly finding a low-dimensional model
of the system controlled by …

arxiv free identification learning linear reinforcement reinforcement learning safety