Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning
This addresses the challenge of multi-objective coordination for robotic teams in security applications, but appears incremental as it focuses on reward function variations without new methods or data.
The paper tackled the problem of designing reward functions for a team of robotic bodyguards protecting a VIP in crowded spaces using deep reinforcement learning, by studying various primitive and composite reward functions and their impact on robot behavior, but did not report concrete numerical results.
We are considering a scenario where a team of bodyguard robots provides physical protection to a VIP in a crowded public space. We use deep reinforcement learning to learn the policy to be followed by the robots. As the robot bodyguards need to follow several difficult-to-reconcile goals, we study several primitive and composite reward functions and their impact on the overall behavior of the robotic bodyguards.