Active Learning for Control-Oriented Identification of Nonlinear Systems

arXiv:2404.09030v1 Announce Type: cross
Abstract: Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a dataset, uses the resulting dataset to identify a model of the system, and finally performs control synthesis using the identified model. As interacting with the system may be costly and time consuming, targeted exploration is crucial for developing an effective …

abstract active learning arxiv community control cs.lg cs.sy dataset eess.sy environment identification identify pipeline reinforcement reinforcement learning systems the environment type