H. U. Sheikh and L. Bölöni

Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning


Cite as:

H. U. Sheikh and L. Bölöni. Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning. In Prof. of 1st Workshop on Goal Specifications for Reinforcement Learning (GoalsRL-2018) at IJCAI 2018, July 2018.

Download:

(unavailable)

Abstract:

In this paper 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.

BibTeX:

@inproceedings{Sheikh-2018-GoalsRL,
   author = "H. U. Sheikh and L. B{\"o}l{\"o}ni",
   booktitle={Prof. of 1st Workshop on Goal Specifications for Reinforcement Learning (GoalsRL-2018) at IJCAI 2018},
   title = "Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning",
   location = "Stockholm, Sweden",
   month = "July",
   year = "2018",
   abstract = {
     In this paper 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.
   }
}

Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Sat Dec 01, 2018 09:52:17