2000 character limit reached
Control-Tutored Reinforcement Learning: an application to the Herding Problem
Published 26 Nov 2019 in cs.LG and cs.AI | (1911.11444v2)
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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.