| Popis: |
The following paragraph was inadvertently omitted from the final version of the paper (Franci & Grammatico, 2022). The paragraph was to be placed at the end of the Introduction section: “Finally, let us remark that our setting, and in general, the literature on SGNEPs, assumes that the agents have access to stochastic (partial) first-order information, specifically, random samples of the pseudogradient, as opposed to zeroth-order information, i.e., direct measurements of the cost functions as in extremum seeking (Frihauf, Krstic, & Basar, 2011; Krilašević & Grammatico, 2021; Liu & Krstić, 2011). In particular, the SGNEP literature assumes that the random samples of first-order information are given, hence cannot be controlled, while the extremum-seeking literature assumes that the available zeroth-order information is deterministic and results from a controlled perturbation injected into the system”. |
Full Text from ScienceDirect