4 citations · 15 across the 9 of their papers we have counts for
4 papers · 1 filter
Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets
Stefano Covone, Italo Napolitano, Francesco De Lellis +1
We propose a decentralized reinforcement learning solution for multi-agent shepherding of non-cohesive targets using policy-gradient methods. Our architecture integrates target-sel…
CT-DQN: Control-Tutored Deep Reinforcement Learning
Francesco De Lellis, Marco Coraggio, Giovanni Russo +2
One of the major challenges in Deep Reinforcement Learning for control is the need for extensive training to learn the policy. Motivated by this, we present the design of the Contr…
Control-Tutored Reinforcement Learning: Towards the Integration of Data-Driven and Model-Based Control
F. De Lellis, M. Coraggio, G. Russo +2
We present an architecture where a feedback controller derived on an approximate model of the environment assists the learning process to enhance its data efficiency. This architec…
Control-Tutored Reinforcement Learning: an application to the Herding Problem
Francesco De Lellis, Fabrizia Auletta, Giovanni Russo +1
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 s…