We exploit a control-tutored reinforcement learning (CTRL) algorithm to solve the herding problem. We illustrate the benefits of our approach and its effectiveness by using the problem of controlling one or more agents to herd and contain within a goal region a set of target free-roving agents in the plane.
An Application of Control-Tutored Reinforcement Learning to the Herding Problem / De Lellis, F.; Auletta, F.; Russo, G.; De Lellis, P.; Di Bernardo, M.. - 2021-:(2021), pp. 1-4. (Intervento presentato al convegno 17th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2021 tenutosi a ita nel 2021) [10.1109/CNNA49188.2021.9610789].
An Application of Control-Tutored Reinforcement Learning to the Herding Problem
De Lellis F.;De Lellis P.;Di Bernardo M.
2021
Abstract
We exploit a control-tutored reinforcement learning (CTRL) algorithm to solve the herding problem. We illustrate the benefits of our approach and its effectiveness by using the problem of controlling one or more agents to herd and contain within a goal region a set of target free-roving agents in the plane.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
