Control-Tutored Reinforcement Learning: an application to the Herding Problem

2019-11-26Unverified0· sign in to hype

Francesco De Lellis, Fabrizia Auletta, Giovanni Russo, Mario di Bernardo

Unverified — Be the first to reproduce this paper.

Abstract

In this extended abstract we introduce a novel control-tutored Q-learning approach (CTQL) as part of the ongoing effort in developing model-based and safe RL for continuous state spaces. We validate our approach by applying it to a challenging multi-agent herding control problem.

Tasks

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Control-Tutored Reinforcement Learning: an application to the Herding Problem

Abstract

Tasks

Reproductions